AI Research News Feeds for October 14th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
• MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expression
• Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
• MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference
• Robust Ego-Exo Correspondence with Long-Term Memory
• Enhancing Maritime Domain Awareness on Inland Waterways: A YOLO-Based Fusion of Satellite and AIS for Vessel Characterization
• Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion
• VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
• Towards Fast and Scalable Normal Integration using Continuous Components
• Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
• mmWalk: Towards Multi-modal Multi-view Walking Assistance
• Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
• ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?
• How many samples to label for an application given a foundation model? Chest X-ray classification study
• SNAP: Towards Segmenting Anything in Any Point Cloud
• A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation
• Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
• MS-Mix: Unveiling the Power of Mixup for Multimodal Sentiment Analysis
• ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training
• ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
• High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
• IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
• PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
• InfiniHuman: Infinite 3D Human Creation with Precise Control
• Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View
• Diffusion Transformers with Representation Autoencoders
• Bayesian Topological Convolutional Neural Nets
• DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
• Point Prompting: Counterfactual Tracking with Video Diffusion Models
• Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streams
• Semantic-Cohesive Knowledge Distillation for Deep Cross-modal Hashing
• Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
• Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
• Cross-Sensor Touch Generation
• Decomposer Networks: Deep Component Analysis and Synthesis
• MTMD: A Multi-Task Multi-Domain Framework for Unified Ad Lightweight Ranking at Pinterest
• Generative Latent Video Compression
• CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting
• SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
• Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts
• INR-Bench: A Unified Benchmark for Implicit Neural Representations in Multi-Domain Regression and Reconstruction
• Towards Efficient 3D Gaussian Human Avatar Compression: A Prior-Guided Framework
• SuperEx: Enhancing Indoor Mapping and Exploration using Non-Line-of-Sight Perception
• SpikeGrasp: A Benchmark for 6-DoF Grasp Pose Detection from Stereo Spike Streams
• UltraScatter: Ray-Based Simulation of Ultrasound Scattering
• ImpMIA: Leveraging Implicit Bias for Membership Inference Attack under Realistic Scenarios
• JND-Guided Light-Weight Neural Pre-Filter for Perceptual Image Coding
• VLM-Guided Adaptive Negative Prompting for Creative Generation
• Comparative Evaluation of Neural Network Architectures for Generalizable Human Spatial Preference Prediction in Unseen Built Environments
• On the Optimal Representation Efficiency of Barlow Twins: An Information-Geometric Interpretation
• The Easy Path to Robustness: Coreset Selection using Sample Hardness
• Lightweight Facial Landmark Detection in Thermal Images via Multi-Level Cross-Modal Knowledge Transfer
• SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy
• Invariant Feature Learning for Generalized Long-Tailed Classification
• Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization
• Information Topology
• Hyper-STTN: Hypergraph Augmented Spatial-Temporal Transformer Network for Trajectory Prediction
• MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining
• Improving Hierarchical Representations of Vectorized HD Maps with Perspective Clues
• UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning
• Streamlining Image Editing with Layered Diffusion Brushes
• RATLIP: Generative Adversarial CLIP Text-to-Image Synthesis Based on Recurrent Affine Transformations
• A Unified Approach Towards Active Learning and Out-of-Distribution Detection
• SMC++: Masked Learning of Unsupervised Video Semantic Compression
• Contrastive Local Manifold Learning for No-Reference Image Quality Assessment
• Open Vocabulary Multi-Label Video Classification
• LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting
• Tokenizing Motion: A Generative Approach for Scene Dynamics Compression
• OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
• Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction
• Multimodal Alignment and Fusion: A Survey
• Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval
• Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
• Real-Time Position-Aware View Synthesis from Single-View Input
• CULTURE3D: A Large-Scale and Diverse Dataset of Cultural Landmarks and Terrains for Gaussian-Based Scene Rendering
• Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations
• Generating Multi-Image Synthetic Data for Text-to-Image Customization
• FCVSR: A Frequency-aware Method for Compressed Video Super-Resolution
• MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification
• OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
• Blind Video Super-Resolution based on Implicit Kernels
• Isolated Channel Vision Transformers: From Single-Channel Pretraining to Multi-Channel Finetuning
• A Comprehensive Survey on Knowledge Distillation
• Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
• Surface-Aware Distilled 3D Semantic Features
• SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance
• VideoAds for Fast-Paced Video Understanding
• DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion
• LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detection
• Motion-Enhanced Nonlocal Similarity Implicit Neural Representation for Infrared Dim and Small Target Detection
• xTrace: A Facial Expressive Behaviour Analysis Tool for Continuous Affect Recognition
• CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
• InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
• VORTA: Efficient Video Diffusion via Routing Sparse Attention
• SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams
• Learning Shared Representations from Unpaired Data
• Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control
• SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
• Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments
• Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization
• A PDE-Based Image Dehazing Method via Atmospheric Scattering Theory
• OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
• LH2Face: Loss function for Hard High-quality Face
• DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy
• SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
• Multi-Scale Attention and Gated Shifting for Fine-Grained Event Spotting in Videos
• STAR: A Benchmark for Astronomical Star Fields Super-Resolution
• IONext: Unlocking the Next Era of Inertial Odometry
• Rethinking Medical Anomaly Detection in Brain MRI: An Image Quality Assessment Perspective
• Cell as Point: One-Stage Framework for Efficient Cell Tracking
• LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
• Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing
• Demand Estimation with Text and Image Data
• MedVKAN: Efficient Feature Extraction with Mamba and KAN for Medical Image Segmentation
• OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
• Large-Area Fabrication-Aware Computational Diffractive Optics
• Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
• TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores
• The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
• Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey
• Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
• Post Processing of image segmentation using Conditional Random Fields
• Exploration of Incremental Synthetic Non-Morphed Images for Single Morphing Attack Detection
• Cell Instance Segmentation: The Devil Is in the Boundaries
• Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation
• Fast Self-Supervised depth and mask aware Association for Multi-Object Tracking
• Geometry-Aware Scene Configurations for Novel View Synthesis
• LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
• An uncertainty-aware framework for data-efficient multi-view animal pose estimation
• HeadsUp! High-Fidelity Portrait Image Super-Resolution
• Semi-disentangled spatiotemporal implicit neural representations of longitudinal neuroimaging data for trajectory classification
• A Multi-Strategy Framework for Enhancing Shatian Pomelo Detection in Real-World Orchards
• J-RAS: Enhancing Medical Image Segmentation via Retrieval-Augmented Joint Training
• Scaling Traffic Insights with AI and Language Model-Powered Camera Systems for Data-Driven Transportation Decision Making
• FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
• BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes
• MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output
• Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning
• P-4DGS: Predictive 4D Gaussian Splatting with 90$\times$ Compression
• Complementary and Contrastive Learning for Audio-Visual Segmentation
• DREAM: A Benchmark Study for Deepfake REalism AssessMent
• Collaborative Learning of Semantic-Aware Feature Learning and Label Recovery for Multi-Label Image Recognition with Incomplete Labels
• Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning
• Tracking the Spatiotemporal Evolution of Landslide Scars Using a Vision Foundation Model: A Novel and Universal Framework
• Gesplat: Robust Pose-Free 3D Reconstruction via Geometry-Guided Gaussian Splatting
• Cooperative Pseudo Labeling for Unsupervised Federated Classification
• Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models
• ImmerIris: A Large-Scale Dataset and Benchmark for Immersive Iris Recognition in Open Scenes
• Multi Class Parkinsons Disease Detection Based on Finger Tapping Using Attention-Enhanced CNN BiLSTM
• YOLOv11-Litchi: Efficient Litchi Fruit Detection based on UAV-Captured Agricultural Imagery in Complex Orchard Environments
• Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer
• Stroke Locus Net: Occluded Vessel Localization from MRI Modalities
• ReMix: Towards a Unified View of Consistent Character Generation and Editing
• SparseUWSeg: Active Sparse Point-Label Augmentation for Underwater Semantic Segmentation
• ViConEx-Med: Visual Concept Explainability via Multi-Concept Token Transformer for Medical Image Analysis
• TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval
• Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification
• B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding
• From Generic to Specialized: A Subspecialty Diagnostic System Powered by Self-Supervised Learning for Cervical Histopathology
• A Style-Based Metric for Quantifying the Synthetic-to-Real Gap in Autonomous Driving Image Datasets
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images
• Are Video Models Emerging as Zero-Shot Learners and Reasoners in Medical Imaging?
• Opacity-Gradient Driven Density Control for Compact and Efficient Few-Shot 3D Gaussian Splatting
• VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework
• Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking
• SAM2LoRA: Composite Loss-Guided, Parameter-Efficient Finetuning of SAM2 for Retinal Fundus Segmentation
• Ordinal Scale Traffic Congestion Classification with Multi-Modal Vision-Language and Motion Analysis
• PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
• Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure
• Self-Supervised Multi-Scale Transformer with Attention-Guided Fusion for Efficient Crack Detection
• AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
• Guided Image Feature Matching using Feature Spatial Order
• Towards Cybersickness Severity Classification from VR Gameplay Videos Using Transfer Learning and Temporal Modeling
• MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
• Post-TIPS Prediction via Multimodal Interaction: A Multi-Center Dataset and Framework for Survival, Complication, and Portal Pressure Assessment
• When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance
• DAGLFNet:Deep Attention-Guided Global-Local Feature Fusion for Pseudo-Image Point Cloud Segmentation
• MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition
• Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation
• Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking
• VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
• Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks
• Unified Open-World Segmentation with Multi-Modal Prompts
• Layout-Independent License Plate Recognition via Integrated Vision and Language Models
• MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates
• MRS-YOLO Railroad Transmission Line Foreign Object Detection Based on Improved YOLO11 and Channel Pruning
• Deep semi-supervised approach based on consistency regularization and similarity learning for weeds classification
• UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
• Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes
• Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection
• A Simple and Better Baseline for Visual Grounding
• ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
• OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment
• GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus
• A Machine Learning Perspective on Automated Driving Corner Cases
• Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping
• AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes
• MSM-Seg: A Modality-and-Slice Memory Framework with Category-Agnostic Prompting for Multi-Modal Brain Tumor Segmentation
• Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding
• Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
• Uncovering Anomalous Events for Marine Environmental Monitoring via Visual Anomaly Detection
• Restricted Receptive Fields for Face Verification
• EGD-YOLO: A Lightweight Multimodal Framework for Robust Drone-Bird Discrimination via Ghost-Enhanced YOLOv8n and EMA Attention under Adverse Condition
• Structured Spectral Graph Learning for Multi-label Abnormality Classification in 3D Chest CT Scans
• ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling
• Full segmentation annotations of 3D time-lapse microscopy images of MDA231 cells
• FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding
• rareboost3d: a synthetic lidar dataset with enhanced rare classes
• Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
• SceneTextStylizer: A Training-Free Scene Text Style Transfer Framework with Diffusion Model
• DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects
• Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priors
• IUT-Plug: A Plug-in tool for Interleaved Image-Text Generation
• Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning
• Mixup Helps Understanding Multimodal Video Better
• Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
• ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation
• Frequency Domain Unlocks New Perspectives for Abdominal Medical Image Segmentation
• COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models
• High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
• GIR-Bench: Versatile Benchmark for Generating Images with Reasoning
• Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
• Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts
• Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset
• Zero-shot Face Editing via ID-Attribute Decoupled Inversion
• LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation
• ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer
• Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
• CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization
• Compositional Zero-Shot Learning: A Survey
• MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps
• Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
• Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
• Demystifying Numerosity in Diffusion Models -- Limitations and Remedies
• Validation of an Artificial Intelligence Tool for the Detection of Sperm DNA Fragmentation Using the TUNEL In Situ Hybridization Assay
• Multiview Manifold Evidential Fusion for PolSAR Image Classification
• CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
• Reliable Cross-modal Alignment via Prototype Iterative Construction
• BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models
• Saudi Sign Language Translation Using T5
• FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
• Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos
• Investigating Identity Signals in Conversational Facial Dynamics via Disentangled Expression Features
• DTEA: Dynamic Topology Weaving and Instability-Driven Entropic Attenuation for Medical Image Segmentation
• Exploring and Leveraging Class Vectors for Classifier Editing
• EEMS: Edge-Prompt Enhanced Medical Image Segmentation Based on Learnable Gating Mechanism
• Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering
• $\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
• sketch2symm: Symmetry-aware sketch-to-shape generation via semantic bridging
• Evaluating the effects of preprocessing, method selection, and hyperparameter tuning on SAR-based flood mapping and water depth estimation
• REACT3D: Recovering Articulations for Interactive Physical 3D Scenes
• Steering Over-refusals Towards Safety in Retrieval Augmented Generation
• End-to-end Speech Recognition with similar length speech and text
• Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?
• When or What? Understanding Consumer Engagement on Digital Platforms
• VOLTAGE: A Versatile Contrastive Learning based OCR Methodology for ultra low-resource scripts through Auto Glyph Feature Extraction
• Merlin's Whisper: Enabling Efficient Reasoning in LLMs via Black-box Adversarial Prompting
• Detecting Hallucinations in Authentic LLM-Human Interactions
• Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
• FactAppeal: Identifying Epistemic Factual Appeals in News Media
• You're Not Gonna Believe This: A Computational Analysis of Factual Appeals and Sourcing in Partisan News
• Unlocking LLM Safeguards for Low-Resource Languages via Reasoning and Alignment with Minimal Training Data
• RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
• Sarcasm Detection Using Deep Convolutional Neural Networks: A Modular Deep Learning Framework
• Large Language Models for Full-Text Methods Assessment: A Case Study on Mediation Analysis
• HiligayNER: A Baseline Named Entity Recognition Model for Hiligaynon
• Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG
• DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models
• Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks
• LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System
• ADVICE: Answer-Dependent Verbalized Confidence Estimation
• GapDNER: A Gap-Aware Grid Tagging Model for Discontinuous Named Entity Recognition
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF: A Reproducibility Study
• Punctuation-aware treebank tree binarization
• Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
• LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models
• Enabling Doctor-Centric Medical AI with LLMs through Workflow-Aligned Tasks and Benchmarks
• Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
• TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code
• Bridging Gaps in Hate Speech Detection: Meta-Collections and Benchmarks for Low-Resource Iberian Languages
• Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
• Discursive Circuits: How Do Language Models Understand Discourse Relations?
• WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent
• A Theorem-Proving-Based Evaluation of Neural Semantic Parsing
• CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis
• XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
• Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality
• Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
• Are Large Language Models Effective Knowledge Graph Constructors?
• Template-Based Text-to-Image Alignment for Language Accessibility: A Study on Visualizing Text Simplifications
• Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies
• Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification
• Who are you, ChatGPT? Personality and Demographic Style in LLM-Generated Content
• GenCNER: A Generative Framework for Continual Named Entity Recognition
• Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models
• An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
• Information-Preserving Reformulation of Reasoning Traces for Antidistillation
• Invisible Languages of the LLM Universe
• Culturally-Aware Conversations: A Framework & Benchmark for LLMs
• LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
• Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models
• MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
• Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
• StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language Models
• Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation
• ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
• When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents
• Demystifying Reinforcement Learning in Agentic Reasoning
• Are Large Reasoning Models Interruptible?
• A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
• Task-Aware Resolution Optimization for Visual Large Language Models
• CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms
• Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translation
• Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
• The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
• Secret-Protected Evolution for Differentially Private Synthetic Text Generation
• VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents
• ELMO: Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
• Can Tool-Integrated Reinforcement Learning Generalize Across Diverse Domains?
• Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation
• ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
• Bag of Tricks for Subverting Reasoning-based Safety Guardrails
• QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
• REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking
• QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
• Native Language Identification in Turkish: L1 Influence of Arabic, Persian, and Albanian
• Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation
• A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models
• SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs
• Rethinking the Residual Distribution of Locate-then-Editing Methods in Model Editing
• Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents
• Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
• Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
• Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech
• Personality Editing for Language Models through Adjusting Self-Referential Queries
• Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
• Test-Time Alignment for Large Language Models via Textual Model Predictive Control
• Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers
• Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
• Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm
• LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs
• Exploring Compositional Generalization (in COGS/ReCOGS_pos) by Transformers using Restricted Access Sequence Processing (RASP)
• DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation
• Transparent and Robust RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability
• Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
• Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization
• TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
• CrosGrpsABS: Cross-Attention over Syntactic and Semantic Graphs for Aspect-Based Sentiment Analysis in a Low-Resource Language
• ARM: Adaptive Reasoning Model
• Are Language Models Consequentialist or Deontological Moral Reasoners?
• Self-ensemble: Mitigating Confidence Mis-calibration for Large Language Models
• Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks
• Effectiveness of Counter-Speech against Abusive Content: A Multidimensional Annotation and Classification Study
• MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
• When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
• Training and Evaluating with Human Label Variation: An Empirical Study
• DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training
• VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
• Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets
• SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context
• Complexity-aware fine-tuning
• Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations
• TreeNet: Layered Decision Ensembles
• OmniSAT: Compact Action Token, Faster Auto Regression
• Knowledge-Aware Mamba for Joint Change Detection and Classification from MODIS Times Series
• NNDM: NN_UNet Diffusion Model for Brain Tumor Segmentation
• Adaptive Fusion Network with Temporal-Ranked and Motion-Intensity Dynamic Images for Micro-expression Recognition
• Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation
• Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detection
• VisRAG 2.0: Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
• Gold Panning: Turning Positional Bias into Signal for Multi-Document LLM Reasoning
• Steering Embedding Models with Geometric Rotation: Mapping Semantic Relationships Across Languages and Models
• Text Prompt Injection of Vision Language Models
• NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
• CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs
• iBERT: Interpretable Style Embeddings via Sense Decomposition
• DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
• Abductive Preference Learning
• HIPPD: Brain-Inspired Hierarchical Information Processing for Personality Detection
• Don't Throw Away Your Pretrained Model
• Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning
• Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
• Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translations
• MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
• Path Drift in Large Reasoning Models:How First-Person Commitments Override Safety
• HUME: Measuring the Human-Model Performance Gap in Text Embedding Task
• Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference
• A-IPO: Adaptive Intent-driven Preference Optimization
• Diversity Augmentation of Dynamic User Preference Data for Boosting Personalized Text Summarizers
• Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
• LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
• BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data
• Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning
• Text2Token: Unsupervised Text Representation Learning with Token Target Prediction
• ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement
• Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
• On the Entity-Level Alignment in Crosslingual Consistency
• Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy
• End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs
• ASC analyzer: A Python package for measuring argument structure construction usage in English texts
• AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
• RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
• WebThinker: Empowering Large Reasoning Models with Deep Research Capability
• ViDRiP-LLaVA: A Dataset and Benchmark for Diagnostic Reasoning from Pathology Videos
• LiTransProQA: an LLM-based Literary Translation evaluation metric with Professional Question Answering
• Adaptive Stress Testing Black-Box LLM Planners
• CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks
• GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
• DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy
• SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
• A Set-Sequence Model for Time Series
• Simple and Effective Specialized Representations for Fair Classifiers
• A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
• Lightweight and Interpretable Transformer via Mixed Graph Algorithm Unrolling for Traffic Forecast
• Noise Injection Systemically Degrades Large Language Model Safety Guardrails
• Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
• Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
• From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
• Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
• TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning
• DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
• FRIREN: Beyond Trajectories -- A Spectral Lens on Time
• Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain
• Rolling Ball Optimizer: Learning by ironing out loss landscape wrinkles
• STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
• MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
• Multi-Scale Manifold Alignment for Interpreting Large Language Models: A Unified Information-Geometric Framework
• Empirical Investigation of Latent Representational Dynamics in Large Language Models: A Manifold Evolution Perspective
• TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data
• Inclusive, Differentially Private Federated Learning for Clinical Data
• Latent Reasoning via Sentence Embedding Prediction
• Does Machine Unlearning Truly Remove Knowledge?
• Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles
• AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits
• Equivalent Linear Mappings of Large Language Models
• $\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
• State-Covering Trajectory Stitching for Diffusion Planners
• Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN
• Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification
• MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis
• AbBiBench: A Benchmark for Antibody Binding Affinity Maturation and Design
• Superior Molecular Representations from Intermediate Encoder Layers
• Monotone and Conservative Policy Iteration Beyond the Tabular Case
• Revisit What You See: Disclose Language Prior in Vision Tokens for LVLM Decoding
• Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
• Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
• StreetLens: Enabling Human-Centered AI Agents for Neighborhood Assessment from Street View Imagery
• Ignition Phase : Standard Training for Fast Adversarial Robustness
• SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
• Structured Kolmogorov-Arnold Neural ODEs for Interpretable Learning and Symbolic Discovery of Nonlinear Dynamics
• On Convolutions, Intrinsic Dimension, and Diffusion Models
• Doc2SAR: A Synergistic Framework for High-Fidelity Extraction of Structure-Activity Relationships from Scientific Documents
• The Hidden Link Between RLHF and Contrastive Learning
• PULSE: Practical Evaluation Scenarios for Large Multimodal Model Unlearning
• GradMetaNet: An Equivariant Architecture for Learning on Gradients
• MLLM-Fabric: Multimodal Large Language Model-Driven Robotic Framework for Fabric Sorting and Selection
• Train-before-Test Harmonizes Language Model Rankings
• Simulating Three-dimensional Turbulence with Physics-informed Neural Networks
• Learning Diffusion Models with Flexible Representation Guidance
• Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models
• RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services
• A Lightweight and Robust Framework for Real-Time Colorectal Polyp Detection Using LOF-Based Preprocessing and YOLO-v11n
• Learning Representations of Event Time Series with Sparse Autoencoders for Anomaly Detection, Similarity Search, and Unsupervised Classification
• Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
• Efficient Compositional Multi-tasking for On-device Large Language Models
• NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration
• Long-Range Graph Wavelet Networks
• ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy
• Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types
• Protein as a Second Language for LLMs
• RAG-Pull: Imperceptible Attacks on RAG Systems for Code Generation
• Domain-Specific Data Generation Framework for RAG Adaptation
• The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers
• Fairness Metric Design Exploration in Multi-Domain Moral Sentiment Classification using Transformer-Based Models
• LightPneumoNet: Lightweight Pneumonia Classifier
• Attacks by Content: Automated Fact-checking is an AI Security Issue
• Nepali Sign Language Characters Recognition: Dataset Development and Deep Learning Approaches
• Large Language Models Are Effective Code Watermarkers
• A Large-Language-Model Assisted Automated Scale Bar Detection and Extraction Framework for Scanning Electron Microscopic Images
• From Prompts to Packets: A View from the Network on ChatGPT, Copilot, and Gemini
• Towards Real-Time Fake News Detection under Evidence Scarcity
• ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models
• LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
• Beyond touch-based HMI: Control your machines in natural language by utilizing large language models and OPC UA
• When Does Supervised Training Pay Off? The Hidden Economics of Object Detection in the Era of Vision-Language Models
• FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks
• Do LLMs "Feel"? Emotion Circuits Discovery and Control
• Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap
• Event-Aware Prompt Learning for Dynamic Graphs
• Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
• Uncertainty-Aware ControlNet: Bridging Domain Gaps with Synthetic Image Generation
• Multi-View Graph Feature Propagation for Privacy Preservation and Feature Sparsity
• Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
• LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation
• Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
• Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning
• Medical Interpretability and Knowledge Maps of Large Language Models
• DocReward: A Document Reward Model for Structuring and Stylizing
• Living Off the LLM: How LLMs Will Change Adversary Tactics
• KnowRL: Teaching Language Models to Know What They Know
• Reconstructing 12-Lead ECG from 3-Lead ECG using Variational Autoencoder to Improve Cardiac Disease Detection of Wearable ECG Devices
• Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning
• Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers
• Coordinated Strategies in Realistic Air Combat by Hierarchical Multi-Agent Reinforcement Learning
• Investigating Large Language Models' Linguistic Abilities for Text Preprocessing
• AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model
• Offline Reinforcement Learning with Generative Trajectory Policies
• People use fast, flat goal-directed simulation to reason about novel problems
• Automatic Music Sample Identification with Multi-Track Contrastive Learning
• LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
• Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks
• A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services
• CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
• Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
• Characterizing Web Search in The Age of Generative AI
• Hierarchical Qubit-Merging Transformer for Quantum Error Correction
• SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mapping
• LLM-Oriented Token-Adaptive Knowledge Distillation
• Attention Factors for Statistical Arbitrage
• EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
• NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detection
• MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
• FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection
• ManiAgent: An Agentic Framework for General Robotic Manipulation
• FACE: Faithful Automatic Concept Extraction
• Accelerated stochastic first-order method for convex optimization under heavy-tailed noise
• Ego-Vision World Model for Humanoid Contact Planning
• Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
• Representation-Based Exploration for Language Models: From Test-Time to Post-Training
• PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities
• Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation
• Scaling Language-Centric Omnimodal Representation Learning
• Adversarial Attacks Leverage Interference Between Features in Superposition
• CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
• Fake News in Social Networks
• Learning to Be Cautious
• ChipGPT: How far are we from natural language hardware design
• Leveraging Twitter Data for Sentiment Analysis of Transit User Feedback: An NLP Framework
• DeAL: Decoding-time Alignment for Large Language Models
• GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search
• A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
• Human-inspired Episodic Memory for Infinite Context LLMs
• OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
• R-GAT: Cancer Document Classification Leveraging Graph-Based Residual Network for Scenarios with Limited Data
• Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation
• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
• CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
• mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules
• How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
• MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models
• TCP: a Benchmark for Temporal Constraint-Based Planning
• SMELLNET: A Large-scale Dataset for Real-world Smell Recognition
• Agents of Change: Self-Evolving LLM Agents for Strategic Planning
• Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
• Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
• Multi-Functional RIS-Enabled in SAGIN for IoT: A Hybrid Deep Reinforcement Learning Approach with Compressed Twin-Models
• Large Language Models and Operations Research: A Structured Survey
• DeepVARwT: Deep Learning for a VAR Model with Trend
• Meta-Learning Adaptive Loss Functions
• SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition
• Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection
• Minibatch and Local SGD: Algorithmic Stability and Linear Speedup in Generalization
• Codiscovering graphical structure and functional relationships within data: A Gaussian Process framework for connecting the dots
• Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends
• Discovering and Reasoning of Causality in the Hidden World with Large Language Models
• Output Format Biases in the Evaluation of Large Language Models for Code Translation
• Does Biomedical Training Lead to Better Medical Performance?
• The Interpretable and Effective Graph Neural Additive Networks
• A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice
• Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights
• SWIFT: Semantic Watermarking for Image Forgery Thwarting
• MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
• AI-powered skin spectral imaging enables instant sepsis diagnosis and outcome prediction in critically ill patients
• QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
• Automated detection of underdiagnosed medical conditions via opportunistic imaging
• Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
• Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classification
• Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge
• FairDD: Fair Dataset Distillation
• Robot Learning with Super-Linear Scaling
• Edge Delayed Deep Deterministic Policy Gradient: efficient continuous control for edge scenarios
• Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning
• SEKE: Specialised Experts for Keyword Extraction
• TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training
• Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
• On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning
• Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
• Contrastive Representation Distillation via Multi-Scale Feature Decoupling
• The Minimal Search Space for Conditional Causal Bandits
• Auction Design using Value Prediction with Hallucinations
• AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers
• DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
• Precise Mobile Manipulation of Small Everyday Objects
• Steering LLMs for Formal Theorem Proving
• Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
• Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
• MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
• Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
• Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft
• On the Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions
• Learning to Instruct for Visual Instruction Tuning
• Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation
• PartialLoading: User Scheduling and Bandwidth Allocation for Parameter-sharing Edge Inference
• VNJPTranslate: A comprehensive pipeline for Vietnamese-Japanese translation
• Frontier AI's Impact on the Cybersecurity Landscape
• Deep Learning-based Intrusion Detection Systems: A Survey
• BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning
• Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data
• Forecasting Clinical Risk from Textual Time Series: Structuring Narratives for Temporal AI in Healthcare
• QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning
• You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
• SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification
• Reasoning-Enhanced Large Language Models for Molecular Property Prediction
• MRI Brain Tumor Detection with Computer Vision
• Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models
• Unveiling Gamer Archetypes through Multi modal feature Correlations and Unsupervised Learning
• MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
• X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
• ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
• From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
• MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
• The algorithmic regulator
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting
• Prepared for the Unknown: Adapting AIOps Capacity Forecasting Models to Data Changes
• Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
• KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments
• Mapping the Urban Mobility Intelligence Frontier: A Scientometric Analysis of Data-Driven Pedestrian Trajectory Prediction and Simulation
• Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework
• Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harms
• Ortho-Fuse: Orthomosaic Generation for Sparse High-Resolution Crop Health Maps Through Intermediate Optical Flow Estimation
• RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning
• Identifying bias in CNN image classification using image scrambling and transforms
• RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
• STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models
• Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
• Mesh-Gait: A Unified Framework for Gait Recognition Through Multi-Modal Representation Learning from 2D Silhouettes
• LONGQAEVAL: Designing Reliable Evaluations of Long-Form Clinical QA under Resource Constraints
• Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis
• Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs
• Hierarchical LoRA MoE for Efficient CTR Model Scaling
• Multi-Task Learning with Feature-Similarity Laplacian Graphs for Predicting Alzheimer's Disease Progression
• Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance
• Reverse Supervision at Scale: Exponential Search Meets the Economics of Annotation
• Data-driven simulator of multi-animal behavior with unknown dynamics via offline and online reinforcement learning
• NIM: Neuro-symbolic Ideographic Metalanguage for Inclusive Communication
• Testing and Enhancing Multi-Agent Systems for Robust Code Generation
• Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation
• LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting
• AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
• FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth
• Assessing Large Language Models for Structured Medical Order Extraction
• Latent Retrieval Augmented Generation of Cross-Domain Protein Binders
• UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models
• SASER: Stego attacks on open-source LLMs
• Towards Self-Refinement of Vision-Language Models with Triangular Consistency
• Personalized Motion Guidance Framework for Athlete-Centric Coaching
• Align2Act: Instruction-Tuned Models for Human-Aligned Autonomous Driving
• MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
• f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
• Population-Coded Spiking Neural Networks for High-Dimensional Robotic Control
• ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs
• Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
• PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
• GLOFNet -- A Multimodal Dataset for GLOF Monitoring and Prediction
• BitMar: Low-Bit Multimodal Fusion with Episodic Memory for Edge Devices
• Compositional Symmetry as Compression: Lie Pseudogroup Structure in Algorithmic Agents
• Dynamic Topic Evolution with Temporal Decay and Attention in Large Language Models
• A Machine Learning Approach for MIDI to Guitar Tablature Conversion
• UniCoD: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
• Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
• DEMO: Disentangled Motion Latent Flow Matching for Fine-Grained Controllable Talking Portrait Synthesis
• AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation
• Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection
• BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
• Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey
• LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation
• High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
• Attention-Enhanced LSTM Modeling for Improved Temperature and Rainfall Forecasting in Bangladesh
• Missing Data Multiple Imputation for Tabular Q-Learning in Online RL
• Deep Learning in Astrophysics
• HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing
• SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
• Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits
• Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR
• A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications
• Optimally Deep Networks -- Adapting Model Depth to Datasets for Superior Efficiency
• GPS Spoofing Attack Detection in Autonomous Vehicles Using Adaptive DBSCAN
• Understanding Sampler Stochasticity in Training Diffusion Models for RLHF
• ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis
• DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation
• BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics
• Toward Human-Centered Readability Evaluation
• MSCloudCAM: Cross-Attention with Multi-Scale Context for Multispectral Cloud Segmentation
• PruneGCRN: Minimizing and explaining spatio-temporal problems through node pruning
• Therapeutic AI and the Hidden Risks of Over-Disclosure: An Embedded AI-Literacy Framework for Mental Health Privacy
• Is Implicit Knowledge Enough for LLMs? A RAG Approach for Tree-based Structures
• Generative AI and the Transformation of Software Development Practices
• From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis
• Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
• Happiness is Sharing a Vocabulary: A Study of Transliteration Methods
• VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
• Software Defect Prediction using Autoencoder Transformer Model
• Discrete State Diffusion Models: A Sample Complexity Perspective
• HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
• GRIP: A Unified Framework for Grid-Based Relay and Co-Occurrence-Aware Planning in Dynamic Environments
• Generative AI for Software Project Management: Insights from a Review of Software Practitioner Literature
• Topological Alignment of Shared Vision-Language Embedding Space
• LPCVAE: A Conditional VAE with Long-Term Dependency and Probabilistic Time-Frequency Fusion for Time Series Anomaly Detection
• DreamMakeup: Face Makeup Customization using Latent Diffusion Models
• Comparative Explanations via Counterfactual Reasoning in Recommendations
• FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
• Evaluating Language Models' Evaluations of Games
• TabVLA: Targeted Backdoor Attacks on Vision-Language-Action Models
• Redundancy as a Structural Information Principle for Learning and Generalization
• Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank
• Project-Level C-to-Rust Translation via Synergistic Integration of Knowledge Graphs and Large Language Models
• Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
• KOTOX: A Korean Toxic Dataset for Deobfuscation and Detoxification
• MC#: Mixture Compressor for Mixture-of-Experts Large Models
• APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport
• Judge Before Answer: Can MLLM Discern the False Premise in Question?
• RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection
• Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
• DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
• A Survey on Agentic Multimodal Large Language Models
• DeepResearchGuard: Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety
• ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
• DND: Boosting Large Language Models with Dynamic Nested Depth
• Automating Structural Engineering Workflows with Large Language Model Agents
• Into the Unknown: Towards using Generative Models for Sampling Priors of Environment Uncertainty for Planning in Configuration Spaces
• GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation
• XGrasp: Gripper-Aware Grasp Detection with Multi-Gripper Data Generation
• From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance
• Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
• PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System
• Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
• Causal Disentanglement Learning for Accurate Anomaly Detection in Multivariate Time Series
• Source-Free Object Detection with Detection Transformer
• Text-Enhanced Panoptic Symbol Spotting in CAD Drawings
• HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
• A Primer on SO(3) Action Representations in Deep Reinforcement Learning
• Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization
• A Vision for Access Control in LLM-based Agent Systems
• PhysioME: A Robust Multimodal Self-Supervised Framework for Physiological Signals with Missing Modalities
• video-SALMONN S: Streaming Audio-Visual LLMs Beyond Length Limits via Memory
• One Size Does Not Fit All: Exploring Variable Thresholds for Distance-Based Multi-Label Text Classification
• EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling
• G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation
• Responsible AI Adoption in the Public Sector: A Data-Centric Taxonomy of AI Adoption Challenges
• Bias-Aware AI Chatbot for Engineering Advising at the University of Maryland A. James Clark School of Engineering
• Direct Routing Gradient (DRGrad): A Personalized Information Surgery for Multi-Task Learning (MTL) Recommendations
• Enhanced Urban Traffic Management Using CCTV Surveillance Videos and Multi-Source Data Current State Prediction and Frequent Episode Mining
• Real-Time Health Analytics Using Ontology-Driven Complex Event Processing and LLM Reasoning: A Tuberculosis Case Study
• Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
• TinyViT-Batten: Few-Shot Vision Transformer with Explainable Attention for Early Batten-Disease Detection on Pediatric MRI
• Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition
• Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
• Generative Models for Helmholtz Equation Solutions: A Dataset of Acoustic Materials
• Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models
• Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
• Adversarial-Resilient RF Fingerprinting: A CNN-GAN Framework for Rogue Transmitter Detection
• A Hybrid Computational Intelligence Framework with Metaheuristic Optimization for Drug-Drug Interaction Prediction
• Leveraging LLMs to Streamline the Review of Public Funding Applications
• Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
• AI in Computational Thinking Education in Higher Education: A Systematic Literature Review
• Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices
• Deep Neural Networks Inspired by Differential Equations
• Stop DDoS Attacking the Research Community with AI-Generated Survey Papers
• On the Occurence of Critical Learning Periods in Neural Networks
• CREST-Search: Comprehensive Red-teaming for Evaluating Safety Threats in Large Language Models Powered by Web Search
• Evaluation of Differential Privacy Mechanisms on Federated Learning
• Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
• Vanishing Contributions: A Unified Approach to Smoothly Transition Neural Models into Compressed Form
• VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands
• A Demonstration of Self-Adaptive Jamming Attack Detection in AI/ML Integrated O-RAN
• The Idola Tribus of AI: Large Language Models tend to perceive order where none exists
• SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
• ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models
• Group-Adaptive Adversarial Learning for Robust Fake News Detection Against Malicious Comments
• All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
• High-Power Training Data Identification with Provable Statistical Guarantees
• ICL-Router: In-Context Learned Model Representations for LLM Routing
• Preference-Aware Memory Update for Long-Term LLM Agents
• Layout-Aware Parsing Meets Efficient LLMs: A Unified, Scalable Framework for Resume Information Extraction and Evaluation
• It's 2025 -- Narrative Learning is the new baseline to beat for explainable machine learning
• InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation
• Herb.jl: A Unifying Program Synthesis Library
• Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction
• ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting
• InterCorpRel-LLM: Enhancing Financial Relational Understanding with Graph-Language Models
• Chlorophyll-a Mapping and Prediction in the Mar Menor Lagoon Using C2RCC-Processed Sentinel 2 Imagery
• Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement
• Machine learning methods fail to provide cohesive atheoretical construction of personality traits from semantic embeddings
• Patentformer: A demonstration of AI-assisted automated patent drafting
• PatentVision: A multimodal method for drafting patent applications
• Scaling Laws and Symmetry, Evidence from Neural Force Fields
• PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection
• Why Do Transformers Fail to Forecast Time Series In-Context?
• SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasters
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
• Large Language Models for Imbalanced Classification: Diversity makes the difference
• Temporal Lifting as Latent-Space Regularization for Continuous-Time Flow Models in AI Systems
• Towards Understanding Ambiguity Resolution in Multimodal Inference of Meaning
• Harnessing Self-Supervised Deep Learning and Geostationary Remote Sensing for Advancing Wildfire and Associated Air Quality Monitoring: Improved Smoke and Fire Front Masking using GOES and TEMPO Radiance Data
• CALM: A Causal Analysis Language Model for Tabular Data in Complex Systems with Local Scores, Conditional Independence Tests, and Relation Attributes
• ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
• Token is All You Price
• NarraBench: A Comprehensive Framework for Narrative Benchmarking
• WARC-Bench: Web Archive Based Benchmark for GUI Subtask Executions
• ROBOPSY PL[AI]: Using Role-Play to Investigate how LLMs Present Collective Memory
• Myopic Bayesian Decision Theory for Batch Active Learning with Partial Batch Label Sampling
• CHUG: Crowdsourced User-Generated HDR Video Quality Dataset
• Closing the Data-Efficiency Gap Between Autoregressive and Masked Diffusion LLMs
• Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentration
• Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings
• Learning Bug Context for PyTorch-to-JAX Translation with LLMs
• Stability of Transformers under Layer Normalization
• Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem
• SpectralCA: Bi-Directional Cross-Attention for Next-Generation UAV Hyperspectral Vision
• Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery
• Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications
• MemPromptTSS: Persistent Prompt Memory for Iterative Multi-Granularity Time Series State Segmentation
• Denoising Diffusion as a New Framework for Underwater Images
• Unpacking Hateful Memes: Presupposed Context and False Claims
• Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding
• Explainable Human-in-the-Loop Segmentation via Critic Feedback Signals
• Beyond Fertility: Analyzing STRR as a Metric for Multilingual Tokenization Evaluation
• Homomorphic Mappings for Value-Preserving State Aggregation in Markov Decision Processes
• Operationalizing AI: Empirical Evidence on MLOps Practices, User Satisfaction, and Organizational Context
• Neuro-inspired automated lens design
• Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning
• SLEAN: Simple Lightweight Ensemble Analysis Network for Multi-Provider LLM Coordination: Design, Implementation, and Vibe Coding Bug Investigation Case Study
• Skill-Targeted Adaptive Training
• Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Default
• Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimization
• FOSSIL: Regret-Minimizing Curriculum Learning for Metadata-Free and Low-Data Mpox Diagnosis
• ALLOY: Generating Reusable Agent Workflows from User Demonstration
• Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
• Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling
• CLMN: Concept based Language Models via Neural Symbolic Reasoning
• OBsmith: Testing JavaScript Obfuscator using LLM-powered sketching
• Gradient-based Model Shortcut Detection for Time Series Classification
• How AI Companionship Develops: Evidence from a Longitudinal Study
• Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
• What Makes Looped Transformers Perform Better Than Non-Recursive Ones (Provably)
• Uncovering Singularities in Feynman Integrals via Machine Learning
• Uncertainty-Aware Post-Detection Framework for Enhanced Fire and Smoke Detection in Compact Deep Learning Models
• Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization
• DeepFusionNet: Autoencoder-Based Low-Light Image Enhancement and Super-Resolution
• Ctrl-World: A Controllable Generative World Model for Robot Manipulation
• CacheClip: Accelerating RAG with Effective KV Cache Reuse
• PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
• Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task
• DiffHeads: Differential Analysis and Inference-Time Masking of Bias Heads in Large Language Models
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
• Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
• BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
• Multi-Scale Diffusion Transformer for Jointly Simulating User Mobility and Mobile Traffic Pattern
• SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation
• Large Language Model Sourcing: A Survey
• HccePose(BF): Predicting Front \& Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
• LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models
• Dejavu: Post-Deployment Learning for Embodied Agents via Experience Feedback
• A Survey of Inductive Reasoning for Large Language Models
• MedAgentAudit: Diagnosing and Quantifying Collaborative Failure Modes in Medical Multi-Agent Systems
• Formally Verified Certification of Unsolvability of Temporal Planning Problems
• CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
• Revisiting Trust in the Era of Generative AI: Factorial Structure and Latent Profiles
• RLFR: Extending Reinforcement Learning for LLMs with Flow Environment
• Distributionally Robust Control with End-to-End Statistically Guaranteed Metric Learning
• Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis
• UF-RNN: Real-Time Adaptive Motion Generation Using Uncertainty-Driven Foresight Prediction
• A3RNN: Bi-directional Fusion of Bottom-up and Top-down Process for Developmental Visual Attention in Robots
• The Geometry of Reasoning: Flowing Logics in Representation Space
• How can we assess human-agent interactions? Case studies in software agent design
• AI and Consciousness
• Beyond AlphaEarth: Toward Human-Centered Spatial Representation via POI-Guided Contrastive Learning
• Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
• The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
• Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs
• Deliberative Dynamics and Value Alignment in LLM Debates
• RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning
• Failure-Driven Workflow Refinement
• Belief Graphs with Reasoning Zones: Structure, Dynamics, and Epistemic Activation
• SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning
• SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation
• Agentic Troubleshooting Guide Automation for Incident Management
• DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
• CharCom: Composable Identity Control for Multi-Character Story Illustration
• Concise Reasoning in the Lens of Lagrangian Optimization
• SAFER: Risk-Constrained Sample-then-Filter in Large Language Models
• Don't Just Fine-tune the Agent, Tune the Environment
• PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
• Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning
• The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
• Mitigating Hallucination in Multimodal Reasoning via Functional Attention Control
• LLM-Friendly Knowledge Representation for Customer Support
• Beyond Ethics: How Inclusive Innovation Drives Economic Returns in Medical AI
• Trace Length is a Simple Uncertainty Signal in Reasoning Models
• Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction
• MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
• Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
• ELAIPBench: A Benchmark for Expert-Level Artificial Intelligence Paper Understanding
• A Layered Intuition -- Method Model with Scope Extension for LLM Reasoning
• A Distance Measure for Random Permutation Set: From the Layer-2 Belief Structure Perspective
• EA4LLM: A Gradient-Free Approach to Large Language Model Optimization via Evolutionary Algorithms
• Collaborative Text-to-Image Generation via Multi-Agent Reinforcement Learning and Semantic Fusion
• Automatic Piecewise Linear Regression for Predicting Student Learning Satisfaction
• Equity-Aware Geospatial AI for Forecasting Demand-Driven Hospital Locations in Germany
• Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems
• Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning
• Simpliflow: A Lightweight Open-Source Framework for Rapid Creation and Deployment of Generative Agentic AI Workflows
• OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
• Extended Triangular Method: A Generalized Algorithm for Contradiction Separation Based Automated Deduction
• Adaptive Selection of Symbolic Languages for Improving LLM Logical Reasoning
• LLMs as Strategic Agents: Beliefs, Best Response Behavior, and Emergent Heuristics
• DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems
• The Irrational Machine: Neurosis and the Limits of Algorithmic Safety
• LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach
• PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature
• PoU: Proof-of-Use to Counter Tool-Call Hacking in DeepResearch Agents
• Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval
• Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
• Revisiting Model Interpolation for Efficient Reasoning
• FBS Model-based Maintenance Record Accumulation for Failure-Cause Inference in Manufacturing Systems
• Argumentation-Based Explainability for Legal AI: Comparative and Regulatory Perspectives
• Modeling AI-Driven Production and Competitiveness A Multi-Agent Economic Simulation of China and the United States
• Improving AI Efficiency in Data Centres by Power Dynamic Response
• Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis
• $How^{2}$: How to learn from procedural How-to questions
• Aligning Deep Implicit Preferences by Learning to Reason Defensively
• AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?
• PADME: Procedure Aware DynaMic Execution
• Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics
• Automated Skill Decomposition Meets Expert Ontologies: Bridging the Granularity Gap with LLMs
• AI-Driven anemia diagnosis: A review of advanced models and techniques
• From to : Multidimensional Supervision of Reasoning Process for LLM Optimization
• Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
• Zero Data Retention in LLM-based Enterprise AI Assistants: A Comparative Study of Market Leading Agentic AI Products
• Analyzing and Internalizing Complex Policy Documents for LLM Agents
• Reproducibility: The New Frontier in AI Governance
• Explainability, risk modeling, and segmentation based customer churn analytics for personalized retention in e-commerce
• ParaCook: On Time-Efficient Planning for Multi-Agent Systems
• SR-Scientist: Scientific Equation Discovery With Agentic AI
• Operand Quant: A Single-Agent Architecture for Autonomous Machine Learning Engineering
• Detecting Conspiracy Theory Against COVID-19 Vaccines
• Causal Digital Twins for Cyber-Physical Security: A Framework for Robust Anomaly Detection in Industrial Control Systems
• Toward a Unified Security Framework for AI Agents: Trust, Risk, and Liability
• Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Audits