AI Research News Feeds for August 26th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• From Partial Exchangeability to Predictive Probability: A Bayesian Perspective on Classification
• VFOG: Variance-Reduced Fast Optimistic Gradient Methods for a Class of Nonmonotone Generalized Equations
• On the attainment of the Wasserstein--Cramer--Rao lower bound
• LEL: A Novel Lipschitz Continuity-constrained Ensemble Learning Model for EEG-based Emotion Recognition
• AffordanceSAM: Segment Anything Once More in Affordance Grounding
• AnimateAnywhere: Rouse the Background in Human Image Animation
• Mesh-Learner: Texturing Mesh with Spherical Harmonics
• PainFormer: a Vision Foundation Model for Automatic Pain Assessment
• Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields
• VIN-NBV: A View Introspection Network for Next-Best-View Selection
• FaceCrafter: Identity-Conditional Diffusion with Disentangled Control over Facial Pose, Expression, and Emotion
• ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model
• WetCat: Enabling Automated Skill Assessment in Wet-Lab Cataract Surgery Videos
• DiffS-NOCS: 3D Point Cloud Reconstruction through Coloring Sketches to NOCS Maps Using Diffusion Models
• Baltimore Atlas: FreqWeaver Adapter for Semi-supervised Ultra-high Spatial Resolution Land Cover Classification
• BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion
• Boosting Temporal Sentence Grounding via Causal Inference
• Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks
• Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition
• Using Visual Anomaly Detection for Task Execution Monitoring
• A Multimodal Handover Failure Detection Dataset and Baselines
• Joint Quality Assessment and Example-Guided Image Processing by Disentangling Picture Appearance from Content
• Denoising, segmentation and volumetric rendering of optical coherence tomography angiography (OCTA) image using deep learning techniques: a review
• FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real
• Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis
• FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing
• CNeuroMod-THINGS, a densely-sampled fMRI dataset for visual neuroscience
• Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images
• PriorFormer: A Transformer for Real-time Monocular 3D Human Pose Estimation with Versatile Geometric Priors
• GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
• MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models
• 3D latent diffusion models for parameterizing and history matching multiscenario facies systems
• Predicting brain tumour enhancement from non-contrast MR imaging with artificial intelligence
• BrainPath: Generating Subject-Specific Brain Aging Trajectories
• Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning
• Generating Synthetic Contrast-Enhanced Chest CT Images from Non-Contrast Scans Using Slice-Consistent Brownian Bridge Diffusion Network
• MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation
• HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation
• A Survey of Deep Learning-based Point Cloud Denoising
• Deep Learning Architectures for Medical Image Denoising: A Comparative Study of CNN-DAE, CADTra, and DCMIEDNet
• Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
• DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions
• SEBVS: Synthetic Event-based Visual Servoing for Robot Navigation and Manipulation
• Towards Trustworthy Breast Tumor Segmentation in Ultrasound using Monte Carlo Dropout and Deep Ensembles for Epistemic Uncertainty Estimation
• Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model
• TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning
• A holistic perception system of internal and external monitoring for ground autonomous vehicles: AutoTRUST paradigm
• Scene-Agnostic Traversability Labeling and Estimation via a Multimodal Self-supervised Framework
• Deep Face Restoration: A Survey
• Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering
• PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal
• Imperceptible Protection against Style Imitation from Diffusion Models
• Top-Down Guidance for Learning Object-Centric Representations
• PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation
• 3D Feature Distillation with Object-Centric Priors
• CTRL-F: Pairing Convolution with Transformer for Image Classification via Multi-Level Feature Cross-Attention and Representation Learning Fusion
• One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture
• ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
• CARLA2Real: a tool for reducing the sim2real appearance gap in CARLA simulator
• LumiSculpt: Enabling Consistent Portrait Lighting in Video Generation
• V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection
• Neural Shadow Art
• Addressing Text Embedding Leakage in Diffusion-based Image Editing
• CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models
• MSCN: Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles
• Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions
• T*: Re-thinking Temporal Search for Long-Form Video Understanding
• GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
• Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice
• Minimal Solvers for Full DoF Motion Estimation from Asynchronous Tracks
• IDU: Incremental Dynamic Update of Existing 3D Virtual Environments with New Imagery Data
• HERO: Hierarchical Extrapolation and Refresh for Efficient World Models
• TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints
• HotSpotter - Patterned Species Instance Recognition
• A Weighted Vision Transformer-Based Multi-Task Learning Framework for Predicting ADAS-Cog Scores
• JCo-MVTON: Jointly Controllable Multi-Modal Diffusion Transformer for Mask-Free Virtual Try-on
• Improving Interpretability in Alzheimer's Prediction via Joint Learning of ADAS-Cog Scores
• Wound3DAssist: A Practical Framework for 3D Wound Assessment
• HyTver: A Novel Loss Function for Longitudinal Multiple Sclerosis Lesion Segmentation
• FloraSyntropy-Net: Scalable Deep Learning with Novel FloraSyntropy Archive for Large-Scale Plant Disease Diagnosis
• Rethinking the Detail-Preserved Completion of Complex Tubular Structures based on Point Cloud: a Dataset and a Benchmark
• M^3-GloDets: Multi-Region and Multi-Scale Analysis of Fine-Grained Diseased Glomerular Detection
• Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing
• Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset
• CATformer: Contrastive Adversarial Transformer for Image Super-Resolution
• NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction
• F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model
• Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework
• CMFDNet: Cross-Mamba and Feature Discovery Network for Polyp Segmentation
• DroneKey: Drone 3D Pose Estimation in Image Sequences using Gated Key-representation and Pose-adaptive Learning
• From Global to Local: Social Bias Transfer in CLIP
• Sketchpose: Learning to Segment Cells with Partial Annotations
• PoRe: Position-Reweighted Visual Token Pruning for Vision Language Models
• TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration
• HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation
• SCOUT: Semi-supervised Camouflaged Object Detection by Utilizing Text and Adaptive Data Selection
• Box-Level Class-Balanced Sampling for Active Object Detection
• Camera Pose Refinement via 3D Gaussian Splatting
• ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement
• UniAPO: Unified Multimodal Automated Prompt Optimization
• EndoUFM: Utilizing Foundation Models for Monocular depth estimation of endoscopic images
• Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation
• Beam Geometry and Input Dimensionality: Impact on Sparse-Sampling Artifact Correction for Clinical CT with U-Nets
• SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization
• Enhanced Drift-Aware Computer Vision Architecture for Autonomous Driving
• Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization
• Fence off Anomaly Interference: Cross-Domain Distillation for Fully Unsupervised Anomaly Detection
• FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction
• Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
• ArgusCogito: Chain-of-Thought for Cross-Modal Synergy and Omnidirectional Reasoning in Camouflaged Object Segmentation
• Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images
• EventTracer: Fast Path Tracing-based Event Stream Rendering
• Few-shot Unknown Class Discovery of Hyperspectral Images with Prototype Learning and Clustering
• Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance
• GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
• Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
• Interpretable Evaluation of AI-Generated Content with Language-Grounded Sparse Encoders
• Addressing Annotation Scarcity in Hyperspectral Brain Image Segmentation with Unsupervised Domain Adaptation
• NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
• HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis
• RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform Haze
• Local Information Matters: A Rethink of Crowd Counting
• Robust Diagram Reasoning: A Framework for Enhancing LVLM Performance on Visually Perturbed Scientific Diagrams
• Balanced Sharpness-Aware Minimization for Imbalanced Regression
• Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding
• HiCache: Training-free Acceleration of Diffusion Models via Hermite Polynomial-based Feature Caching
• Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation
• Fiducial Marker Splatting for High-Fidelity Robotics Simulations
• Dual Orthogonal Guidance for Robust Diffusion-based Handwritten Text Generation
• Probabilistic Temporal Masked Attention for Cross-view Online Action Detection
• A Novel Local Focusing Mechanism for Deepfake Detection Generalization
• F4-ITS: Fine-grained Feature Fusion for Food Image-Text Search
• M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments
• Styleclone: Face Stylization with Diffusion Based Data Augmentation
• PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
• DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
• REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework
• PD-Loss: Proxy-Decidability for Efficient Metric Learning
• GRASP: Geospatial pixel Reasoning viA Structured Policy learning
• Structural Damage Detection Using AI Super Resolution and Visual Language Model
• Development of an isotropic segmentation model for medial temporal lobe subregions on anisotropic MRI atlas using implicit neural representation
• Advancing Weakly-Supervised Change Detection in Satellite Images via Adversarial Class Prompting
• MMCIG: Multimodal Cover Image Generation for Text-only Documents and Its Dataset Construction via Pseudo-labeling
• Multi-modal Knowledge Decomposition based Online Distillation for Biomarker Prediction in Breast Cancer Histopathology
• 4D Visual Pre-training for Robot Learning
• PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation
• Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
• SEER-VAR: Semantic Egocentric Environment Reasoner for Vehicle Augmented Reality
• AdaGAT: Adaptive Guidance Adversarial Training for the Robustness of Deep Neural Networks
• Spatial-Temporal Human-Object Interaction Detection
• MTNet: Learning modality-aware representation with transformer for RGBT tracking
• FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising
• PosBridge: Multi-View Positional Embedding Transplant for Identity-Aware Image Editing
• First Place Solution to the MLCAS 2025 GWFSS Challenge: The Devil is in the Detail and Minority
• Defending Deepfake via Texture Feature Perturbation
• SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation
• No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection
• DiCache: Let Diffusion Model Determine Its Own Cache
• Lightweight Joint Optimization of General-Purpose Vision-Language Models and Retrievers for Medical Diagnosis
• Enhancing Underwater Images via Deep Learning: A Comparative Study of VGG19 and ResNet50-Based Approaches
• MoCo: Motion-Consistent Human Video Generation via Structure-Appearance Decoupling
• E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation
• Data Leakage in Visual Datasets
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
• Robust Point Cloud Registration via Geometric Overlapping Guided Rotation Search
• TinySR: Pruning Diffusion for Real-World Image Super-Resolution
• An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing
• Disentangled Geometry and Appearance for Efficient Multi-View Surface Reconstruction and Rendering
• Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels
• Investigating Domain Gaps for Indoor 3D Object Detection
• Multi-Level LVLM Guidance for Untrimmed Video Action Recognition
• T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation
• GraphMMP: A Graph Neural Network Model with Mutual Information and Global Fusion for Multimodal Medical Prognosis
• Optimizing Multi-Modal Trackers via Sensitivity-aware Regularized Tuning
• Confidential Prompting: Privacy-preserving LLM Inference on Cloud
• Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation
• AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmark
• Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI
• SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
• Towards High-Precision Depth Sensing via Monocular-Aided iToF and RGB Integration
• CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance
• Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
• MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning
• QA-VLM: Providing human-interpretable quality assessment for wire-feed laser additive manufacturing parts with Vision Language Models
• Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection
• A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontiers
• WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
• Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
• AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results
• Transformer-Based Neural Network for Transient Detection without Image Subtraction
• RF-PGS: Fully-structured Spatial Wireless Channel Representation with Planar Gaussian Splatting
• Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning Benchmark
• Delta-SVD: Efficient Compression for Personalized Text-to-Image Models
• Do Multimodal LLMs See Sentiment?
• AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception
• A Lightweight Convolution and Vision Transformer integrated model with Multi-scale Self-attention Mechanism
• MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
• Structural Energy-Guided Sampling for View-Consistent Text-to-3D
• MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition
• LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR
• Align 3D Representation and Text Embedding for 3D Content Personalization
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• CEIDM: A Controlled Entity and Interaction Diffusion Model for Enhanced Text-to-Image Generation
• HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
• Can AI Have a Personality? Prompt Engineering for AI Personality Simulation: A Chatbot Case Study in Gender-Affirming Voice Therapy Training
• Rethinking Cross-Subject Data Splitting for Brain-to-Text Decoding
• Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers
• ComplexTempQA:A 100m Dataset for Complex Temporal Question Answering
• A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
• Localizing Factual Inconsistencies in Attributable Text Generation
• SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
• Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge
• Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
• Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference
• Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models
• OpenHuEval: Evaluating Large Language Model on Hungarian Specifics
• Post-Training Language Models for Continual Relation Extraction
• Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation
• A Factorized Probabilistic Model of the Semantics of Vague Temporal Adverbials Relative to Different Event Types
• sudoLLM: On Multi-role Alignment of Language Models
• DecisionFlow: Advancing Large Language Model as Principled Decision Maker
• Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication
• Self-Correcting Code Generation Using Small Language Models
• Measuring Sycophancy of Language Models in Multi-turn Dialogues
• Automatic Speech Recognition of African American English: Lexical and Contextual Effects
• Reasoning with RAGged events: RAG-Enhanced Event Knowledge Base Construction and reasoning with proof-assistants
• CoLMbo: Speaker Language Model for Descriptive Profiling
• Modeling Probabilistic Reduction using Information Theory and Naive Discriminative Learning
• Evaluating Scoring Bias in LLM-as-a-Judge
• GoalfyMax: A Protocol-Driven Multi-Agent System for Intelligent Experience Entities
• Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models
• Agri-Query: A Case Study on RAG vs. Long-Context LLMs for Cross-Lingual Technical Question Answering
• SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media
• Toward a Better Localization of Princeton WordNet
• S2Sent: Nested Selectivity Aware Sentence Representation Learning
• DiscussLLM: Teaching Large Language Models When to Speak
• Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation
• Exploring the Interplay between Musical Preferences and Personality through the Lens of Language
• Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundaries
• Demographic Biases and Gaps in the Perception of Sexism in Large Language Models
• From BERT to LLMs: Comparing and Understanding Chinese Classifier Prediction in Language Models
• MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains
• Empirical Analysis of the Effect of Context in the Task of Automated Essay Scoring in Transformer-Based Models
• Leveraging Multi-Source Textural UGC for Neighbourhood Housing Quality Assessment: A GPT-Enhanced Framework
• RephraseTTS: Dynamic Length Text based Speech Insertion with Speaker Style Transfer
• Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol
• Dynamic Embedding of Hierarchical Visual Features for Efficient Vision-Language Fine-Tuning
• DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards
• DS@GT at CheckThat! 2025: A Simple Retrieval-First, LLM-Backed Framework for Claim Normalization
• Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
• Evaluating the Impact of Verbal Multiword Expressions on Machine Translation
• Improving French Synthetic Speech Quality via SSML Prosody Control
• Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
• Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design
• Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions
• EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems
• SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models
• CoCoA: Confidence- and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
• EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning
• Layerwise Importance Analysis of Feed-Forward Networks in Transformer-based Language Models
• SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validation
• Speculating LLMs' Chinese Training Data Pollution from Their Tokens
• Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation
• DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models
• Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning
• Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs
• Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning
• Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs
• Information availability in different languages and various technological constraints related to multilinguism on the Internet
• Feature-Refined Unsupervised Model for Loanword Detection
• German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German
• A Retail-Corpus for Aspect-Based Sentiment Analysis with Large Language Models
• Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
• Speech-Based Depressive Mood Detection in the Presence of Multiple Sclerosis: A Cross-Corpus and Cross-Lingual Study
• Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
• GAICo: A Deployed and Extensible Framework for Evaluating Diverse and Multimodal Generative AI Outputs
• How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
• Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation
• Assess and Prompt: A Generative RL Framework for Improving Engagement in Online Mental Health Communities
• ReProCon: Scalable and Resource-Efficient Few-Shot Biomedical Named Entity Recognition
• LLMs Learn Constructions That Humans Do Not Know
• If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition
• Learning from Diverse Reasoning Paths with Routing and Collaboration
• QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments
• JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences
• ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks
• Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment
• Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs
• Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens
• DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation
• Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding
• Improving Table Understanding with LLMs and Entity-Oriented Search
• A Straightforward Pipeline for Targeted Entailment and Contradiction Detection
• The Power of Framing: How News Headlines Guide Search Behavior
• Geolocation-Aware Robust Spoken Language Identification
• SPORTSQL: An Interactive System for Real-Time Sports Reasoning and Visualization
• Quantifying Language Disparities in Multilingual Large Language Models
• The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum
• Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
• Active Domain Knowledge Acquisition with \$100 Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains
• Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation
• Are You Sure You're Positive? Consolidating Chain-of-Thought Agents with Uncertainty Quantification for Aspect-Category Sentiment Analysis
• From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
• Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language Models
• UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat
• Federated Adversarial Domain Adaptation
• Dynamic Reserve Price Design with Distributed Solving Algorithm
• A Global Optimization Algorithm for K-Center Clustering of One Billion Samples
• Conditional Stochastic Interpolation for Generative Learning
• Does provable absence of barren plateaus imply classical simulability?
• Simulation Based Bayesian Optimization
• SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
• Enhancing the Trainability of Variational Quantum Circuits with Regularization Strategies
• On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
• Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning
• Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
• Fitting Multilevel Factor Models
• Learning from Summarized Data: Gaussian Process Regression with Sample Quasi-Likelihood
• Harnessing Large Language Models for Disaster Management: A Survey
• Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation
• Poisson Hierarchical Indian Buffet Processes-With Indications for Microbiome Species Sampling Models
• TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware
• Learning an Optimal Assortment Policy under Observational Data
• Neural Posterior Estimation for Cataloging Astronomical Images with Spatially Varying Backgrounds and Point Spread Functions
• Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
• CAARMA: Class Augmentation with Adversarial Mixup Regularization
• Optimistic Online Learning in Symmetric Cone Games
• Deep spatio-temporal point processes: Advances and new directions
• Machine Learning-Based Prediction of Quality Shifts on Video Streaming Over 5G
• HMAE: Self-Supervised Few-Shot Learning for Quantum Spin Systems
• Fairmetrics: An R package for group fairness evaluation
• Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
• How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?
• FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models
• Beyond Blur: A Fluid Perspective on Generative Diffusion Models
• Global Convergence of Iteratively Reweighted Least Squares for Robust Subspace Recovery
• FuSeFL: Fully Secure and Scalable Cross-Silo Federated Learning
• On the Foundation of Distributionally Robust Reinforcement Learning
• Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
• Revisiting Differentially Private Hyper-parameter Tuning
• SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
• Tabular and Deep Reinforcement Learning for Gittins Index
• When predict can also explain: few-shot prediction to select better neural latents
• What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering
• Probabilistic Classification of Near-Surface Shallow-Water Sediments using A Portable Free-Fall Penetrometer
• Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
• Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data
• LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
• Active Learning-Based Optimization of Hydroelectric Turbine Startup to Minimize Fatigue Damage
• HeteroTune: Efficient Federated Learning for Large Heterogeneous Models
• ReHub: Linear Complexity Graph Transformers with Adaptive Hub-Spoke Reassignment
• DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization
• An Inquiry into Datacenter TCO for LLM Inference with FP8
• WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models
• Manifold learning in metric spaces
• Understanding Bias Reinforcement in LLM Agents Debate
• Kernel Ridge Regression for Efficient Learning of High-Capacity Hopfield Networks
• Fault Detection in New Wind Turbines with Limited Data by Generative Transfer Learning
• DeeP-Mod: Deep Dynamic Programming based Environment Modelling using Feature Extraction
• Generative Machine Learning in Adaptive Control of Dynamic Manufacturing Processes: A Review
• Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content
• USPR: Learning a Unified Solver for Profiled Routing
• Reconsidering Fairness Through Unawareness From the Perspective of Model Multiplicity
• How to craft a deep reinforcement learning policy for wind farm flow control
• CoxNTF: A New Approach for Joint Clustering and Prediction in Survival Analysis
• Constrained Diffusion Models for Synthesizing Representative Power Flow Datasets
• GUST: Quantifying Free-Form Geometric Uncertainty of Metamaterials Using Small Data
• Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
• Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning
• The Target Polish: A New Approach to Outlier-Resistant Non-Negative Matrix Factorization
• From Small to Large: A Graph Convolutional Network Approach for Solving Assortment Optimization Problems
• HV Metric For Time-Domain Full Waveform Inversion
• Rao Differential Privacy
• Factor Informed Double Deep Learning For Average Treatment Effect Estimation
• Frequency Response Identification of Low-Order Systems: Finite-Sample Analysis
• Integrative Experiments Identify How Punishment Impacts Welfare in Public Goods Games
• On the sample complexity of semi-supervised multi-objective learning
• VROOM - Visual Reconstruction over Onboard Multiview
• Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology
• TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving
• Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks
• CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
• Quickly Tuning Foundation Models for Image Segmentation
• DropLoRA: Sparse Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
• Who Wins the Race? (R Vs Python) - An Exploratory Study on Energy Consumption of Machine Learning Algorithms
• Detecting Struggling Student Programmers using Proficiency Taxonomies
• Programmable k-local Ising Machines and all-optical Kolmogorov-Arnold Networks on Photonic Platforms
• MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models
• Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking
• High-Order Langevin Monte Carlo Algorithms
• Boltzina: Efficient and Accurate Virtual Screening via Docking-Guided Binding Prediction with Boltz-2
• Towards Optimal Convolutional Transfer Learning Architectures for Breast Lesion Classification and ACL Tear Detection
• CausalSent: Interpretable Sentiment Classification with RieszNet
• The Statistical Fairness-Accuracy Frontier
• Citizen Centered Climate Intelligence: Operationalizing Open Tree Data for Urban Cooling and Eco-Routing in Indian Cities
• Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networks
• Segmentation and Classification of Pap Smear Images for Cervical Cancer Detection Using Deep Learning
• ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
• Robust Anomaly Detection in Industrial Environments via Meta-Learning
• A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection
• Diffusion-Based Data Augmentation for Medical Image Segmentation
• Alternating Training-based Label Smoothing Enhances Prompt Generalization
• ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models
• WOMAC: A Mechanism For Prediction Competitions
• Entanglement Detection with Quantum-inspired Kernels and SVMs
• DesCartes Builder: A Tool to Develop Machine-Learning Based Digital Twins
• Unseen Speaker and Language Adaptation for Lightweight Text-To-Speech with Adapters
• Development of a Neural Network Model for Currency Detection to aid visually impaired people in Nigeria
• How Quantization Shapes Bias in Large Language Models
• Incorporating Pre-trained Diffusion Models in Solving the Schr\"odinger Bridge Problem
• Detecting and Characterizing Planning in Language Models
• BirdRecorder's AI on Sky: Safeguarding birds of prey by detection and classification of tiny objects around wind turbines
• SpotEdit: Evaluating Visually-Guided Image Editing Methods
• Hybrid Quantum-Classical Learning for Multiclass Image Classification
• PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation
• Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance
• Introduction to Regularization and Learning Methods for Inverse Problems
• Emerging Semantic Segmentation from Positive and Negative Coarse Label Learning
• Practical GPU Choices for Earth Observation: ResNet-50 Training Throughput on Integrated, Laptop, and Cloud Accelerators
• Clinical characteristics, complications and outcomes of critically ill patients with Dengue in Brazil, 2012-2024: a nationwide, multicentre cohort study
• Flexibility-Conditioned Protein Structure Design with Flow Matching
• Flash Sparse Attention: An Alternative Efficient Implementation of Native Sparse Attention Kernel
• One-step learning algorithm selection for classification via convolutional neural networks
• On the Edge of Memorization in Diffusion Models
• Rethinking Federated Learning Over the Air: The Blessing of Scaling Up
• Adaptive Ensemble Learning with Gaussian Copula for Load Forecasting
• Copyright Protection for 3D Molecular Structures with Watermarking
• Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks
• Multi-layer Abstraction for Nested Generation of Options (MANGO) in Hierarchical Reinforcement Learning
• SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling
• Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
• Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processors
• Multi-domain Distribution Learning for De Novo Drug Design
• Spectrum Prediction in the Fractional Fourier Domain with Adaptive Filtering
• Learning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection Datasets
• Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination
• Generative Feature Imputing - A Technique for Error-resilient Semantic Communication
• Topology Aware Neural Interpolation of Scalar Fields
• A Novel Framework for Uncertainty Quantification via Proper Scores for Classification and Beyond
• Does simple trump complex? Comparing strategies for adversarial robustness in DNNs
• Enhancing Differentially Private Linear Regression via Public Second-Moment
• Riemannian Change Point Detection on Manifolds with Robust Centroid Estimation
• Training Transformers for Mesh-Based Simulations
• Weisfeiler-Lehman meets Events: An Expressivity Analysis for Continuous-Time Dynamic Graph Neural Networks
• FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
• Quantum-Classical Hybrid Framework for Zero-Day Time-Push GNSS Spoofing Detection
• Provable Mixed-Noise Learning with Flow-Matching
• Frozen in Time: Parameter-Efficient Time Series Transformers via Reservoir-Induced Feature Expansion and Fixed Random Dynamics
• Unveiling the Actual Performance of Neural-based Models for Equation Discovery on Graph Dynamical Systems
• HypER: Hyperbolic Echo State Networks for Capturing Stretch-and-Fold Dynamics in Chaotic Flows
• Aligning the Evaluation of Probabilistic Predictions with Downstream Value
• Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI
• HemePLM-Diffuse: A Scalable Generative Framework for Protein-Ligand Dynamics in Large Biomolecular System
• WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition
• Generative Latent Diffusion Model for Inverse Modeling and Uncertainty Analysis in Geological Carbon Sequestration
• Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval
• Analysis of Transferability Estimation Metrics for Surgical Phase Recognition
• Walk-on-Interfaces: A Monte Carlo Estimator for an Elliptic Interface Problem with Nonhomogeneous Flux Jump Conditions and a Neumann Boundary Condition
• TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
• Bootstrapping Conditional Retrieval for User-to-Item Recommendations
• Predictability Enables Parallelization of Nonlinear State Space Models
• The compressible Neural Particle Method for Simulating Compressible Viscous Fluid Flows
• Preserving Domain Generalization in Fine-Tuning via Joint Parameter Selection
• GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
• KL-Regularised Q-Learning: A Token-level Action-Value perspective on Online RLHF
• EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks
• Limitations of refinement methods for weak to strong generalization
• GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection
• CP4SBI: Local Conformal Calibration of Credible Sets in Simulation-Based Inference
• A Decoupled LOB Representation Framework for Multilevel Manipulation Detection with Supervised Contrastive Learning
• Neural Stochastic Differential Equations on Compact State-Spaces
• SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases
• Is the Frequency Principle always valid?
• MetaFed: Advancing Privacy, Performance, and Sustainability in Federated Metaverse Systems
• ShortListing Model: A Streamlined SimplexDiffusion for Discrete Variable Generation
• Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
• ShaLa: Multimodal Shared Latent Space Modelling
• FedERL: Federated Efficient and Robust Learning for Common Corruptions
• Effective Clustering for Large Multi-Relational Graphs
• Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems
• FRAME : Comprehensive Risk Assessment Framework for Adversarial Machine Learning Threats
• Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling
• TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
• Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality
• ReviBranch: Deep Reinforcement Learning for Branch-and-Bound with Revived Trajectories
• A Systematic Literature Review on Multi-label Data Stream Classification
• Adversarial Examples Are Not Bugs, They Are Superposition
• MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
• A Human-In-The-Loop Approach for Improving Fairness in Predictive Business Process Monitoring
• Learning Interpretable Differentiable Logic Networks for Time-Series Classification
• GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-Experts
• Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
• Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
• Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction
• Exploring Efficient Learning of Small BERT Networks with LoRA and DoRA
• ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning
• A Proportional-Integral Controller-Incorporated SGD Algorithm for High Efficient Latent Factor Analysis
• Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning
• Longitudinal Progression Prediction of Alzheimer's Disease with Tabular Foundation Model
• Heterogeneous co-occurrence embedding for visual information exploration
• Towards Synthesizing Normative Data for Cognitive Assessments Using Generative Multimodal Large Language Models
• TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training
• Characterizing the Behavior of Training Mamba-based State Space Models on GPUs
• Neural Contrast Expansion for Explainable Structure-Property Prediction and Random Microstructure Design
• UM3: Unsupervised Map to Map Matching
• Quantifying Out-of-Training Uncertainty of Neural-Network based Turbulence Closures
• Reinforcement-Guided Hyper-Heuristic Hyperparameter Optimization for Fair and Explainable Spiking Neural Network-Based Financial Fraud Detection
• Attention Layers Add Into Low-Dimensional Residual Subspaces
• Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
• Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
• Unveiling the Latent Directions of Reflection in Large Language Models
• Online Learning for Approximately-Convex Functions with Long-term Adversarial Constraints
• Learned Structure in CARTRIDGES: Keys as Shareable Routers in Self-Studied Representations
• Learning ON Large Datasets Using Bit-String Trees
• Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
• MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices
• Stochastic Gradient Descent with Strategic Querying
• Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
• Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection
• Curvature Learning for Generalization of Hyperbolic Neural Networks
• DeepCFD: Efficient near-ground airfoil lift coefficient approximation with deep convolutional neural networks
• Explainable AI (XAI) for Arrhythmia detection from electrocardiograms
• Physics-informed neural network for fatigue life prediction of irradiated austenitic and ferritic/martensitic steels
• AdaptiveK Sparse Autoencoders: Dynamic Sparsity Allocation for Interpretable LLM Representations
• Quantum-Inspired DRL Approach with LSTM and OU Noise for Cut Order Planning Optimization
• CrystalDiT: A Diffusion Transformer for Crystal Generation
• Leveraging the Christoffel Function for Outlier Detection in Data Streams
• Recurrent Transformer U-Net Surrogate for Flow Modeling and Data Assimilation in Subsurface Formations with Faults
• A Novel Unified Extended Matrix for Graph Signal Processing: Theory and Application
• Enhancing Transformer-Based Foundation Models for Time Series Forecasting via Bagging, Boosting and Statistical Ensembles
• AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
• A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context
• OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System
• WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling
• Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speed
• Native Logical and Hierarchical Representations with Subspace Embeddings
• A novel auxiliary equation neural networks method for exactly explicit solutions of nonlinear partial differential equations
• Aligning Distributionally Robust Optimization with Practical Deep Learning Needs
• Deep Learning for Markov Chains: Lyapunov Functions, Poisson's Equation, and Stationary Distributions
• Hyperbolic Multimodal Representation Learning for Biological Taxonomies
• DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs
• Latent Graph Learning in Generative Models of Neural Signals
• Anchor-MoE: A Mean-Anchored Mixture of Experts For Probabilistic Regression
• Uncertainty Propagation Networks for Neural Ordinary Differential Equations
• EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
• Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey
• DRT: Deep Reasoning Translation via Long Chain-of-Thought
• From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning
• Disentangling Exploration of Large Language Models by Optimal Exploitation
• Visual Generation Without Guidance
• SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain
• Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
• 360Brew: A Decoder-only Foundation Model for Personalized Ranking and Recommendation
• TombRaider: Entering the Vault of History to Jailbreak Large Language Models
• Evaluation of Large Language Models via Coupled Token Generation
• Field Matching: an Electrostatic Paradigm to Generate and Transfer Data
• Investigating the Robustness of Deductive Reasoning with Large Language Models
• EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models
• Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models
• Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
• LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
• BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities
• AutoMisty: A Multi-Agent LLM Framework for Automated Code Generation in the Misty Social Robot
• CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation
• MedLoRD: A Medical Low-Resource Diffusion Model for High-Resolution 3D CT Image Synthesis
• HoarePrompt: Structural Reasoning About Program Correctness in Natural Language
• ImF: Implicit Fingerprint for Large Language Models
• Exponentially Weighted Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection Model Training in Unmanned Aerial Vehicles Surveillance Scenarios
• Celler:A Genomic Language Model for Long-Tailed Single-Cell Annotation
• CLaP -- State Detection from Time Series
• X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
• VeriCoder: Enhancing LLM-Based RTL Code Generation through Functional Correctness Validation
• SVD Based Least Squares for X-Ray Pneumonia Classification Using Deep Features
• Theory of Mind in Large Language Models: Assessment and Enhancement
• Multimodal Masked Autoencoder Pre-training for 3D MRI-Based Brain Tumor Analysis with Missing Modalities
• ICQuant: Index Coding enables Low-bit LLM Quantization
• WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
• DSADF: Thinking Fast and Slow for Decision Making
• A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
• From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
• Explainable Prediction of the Mechanical Properties of Composites with CNNs
• Learning with Spike Synchrony in Spiking Neural Networks
• Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
• IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detection
• An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems
• Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
• Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
• Large Language Models in the Task of Automatic Validation of Text Classifier Predictions
• Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
• RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
• Equivariant Spherical Transformer for Efficient Molecular Modeling
• Accountability Attribution: Tracing Model Behavior to Training Processes
• EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
• Auto prompt sql: a resource-efficient architecture for text-to-sql translation in constrained environments
• AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models
• From Legal Texts to Defeasible Deontic Logic via LLMs: A Study in Automated Semantic Analysis
• Effective Red-Teaming of Policy-Adherent Agents
• A foundation model with multi-variate parallel attention to generate neuronal activity
• BiMark: Unbiased Multilayer Watermarking for Large Language Models
• Multi-Level Fusion Graph Neural Network for Molecule Property Prediction
• CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks
• QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
• Leveraging Large Language Models for Accurate Sign Language Translation in Low-Resource Scenarios
• BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
• Explain and Monitor Deep Learning Models for Computer Vision using Obz AI
• Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
• Deep Learning and Matrix Completion-aided IoT Network Localization in the Outlier Scenarios
• KillChainGraph: ML Framework for Predicting and Mapping ATT&CK Techniques
• MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols
• Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data
• ANO : Faster is Better in Noisy Landscape
• SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation
• Bridging Models to Defend: A Population-Based Strategy for Robust Adversarial Defense
• Evasive Active Hypothesis Testing with Deep Neuroevolution: The Single- and Multi-Agent Cases
• Defending against Jailbreak through Early Exit Generation of Large Language Models
• Using LLM for Real-Time Transcription and Summarization of Doctor-Patient Interactions into ePuskesmas in Indonesia: A Proof-of-Concept Study
• Can Large Language Models Act as Ensembler for Multi-GNNs?
• DataTales: A Benchmark for Real-World Intelligent Data Narration
• Scaling Capability in Token Space: An Analysis of Large Vision Language Model
• PRISM: Efficient Long-Range Reasoning With Short-Context LLMs
• SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
• Task Memory Engine (TME): Enhancing State Awareness for Multi-Step LLM Agent Tasks
• Metacognition and Uncertainty Communication in Humans and Large Language Models
• Chemical classification program synthesis using generative artificial intelligence
• Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models
• From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models
• Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy
• Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs
• WHEN TO ACT, WHEN TO WAIT: Modeling the Intent-Action Alignment Problem in Dialogue
• MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
• Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown
• Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA
• When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents
• Understanding visual attention beehind bee-inspired UAV navigation
• Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition
• Adversarial Illusions in Multi-Modal Embeddings
• Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
• Does GPT-4 surpass human performance in linguistic pragmatics?
• The Dual Impact of Virtual Reality: Examining the Addictive Potential and Therapeutic Applications of Immersive Media in the Metaverse
• Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
• Intelligent Condition Monitoring of Industrial Plants: An Overview of Methodologies and Uncertainty Management Strategies
• Optimizing the Design of an Artificial Pancreas to Improve Diabetes Management
• Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining
• History-Aware and Dynamic Client Contribution in Federated Learning
• Optimization-based Prompt Injection Attack to LLM-as-a-Judge
• Quadratic Binary Optimization with Graph Neural Networks
• I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey
• Large Language Models Meet NLP: A Survey
• TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation
• LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation
• Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG
• Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space
• PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
• Visual Evaluative AI: A Hypothesis-Driven Tool with Concept-Based Explanations and Weight of Evidence
• Source Code Summarization in the Era of Large Language Models
• Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks
• Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems
• A Tie-breaking based Local Search Algorithm for Stable Matching Problems
• Orthogonal Finetuning for Direct Preference Optimization
• A Multisource Fusion Framework for Cryptocurrency Price Movement Prediction
• $\mathsf{OPA}$: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning
• FlexTSF: A Flexible Forecasting Model for Time Series with Variable Regularities
• TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
• Watermarking Visual Concepts for Diffusion Models
• MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation
• Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
• Missing Melodies: AI Music Generation and its "Nearly" Complete Omission of the Global South
• Agent-Testing Agent: A Meta-Agent for Automated Testing and Evaluation of Conversational AI Agents
• Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs
• Convergence and Generalization of Anti-Regularization for Parametric Models
• FedKLPR: Personalized Federated Learning for Person Re-Identification with Adaptive Pruning
• Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity
• Optimizing Grasping in Legged Robots: A Deep Learning Approach to Loco-Manipulation
• A Synthetic Dataset for Manometry Recognition in Robotic Applications
• Multimodal Representation Learning Conditioned on Semantic Relations
• DinoTwins: Combining DINO and Barlow Twins for Robust, Label-Efficient Vision Transformers
• TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
• An experimental approach: The graph of graphs
• OmniMRI: A Unified Vision--Language Foundation Model for Generalist MRI Interpretation
• Activation Transport Operators
• LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations
• In-Context Algorithm Emulation in Fixed-Weight Transformers
• MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation
• UQ: Assessing Language Models on Unsolved Questions
• RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
• GWM: Towards Scalable Gaussian World Models for Robotic Manipulation
• Steering When Necessary: Flexible Steering Large Language Models with Backtracking
• Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit
• ControlEchoSynth: Boosting Ejection Fraction Estimation Models via Controlled Video Diffusion
• Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes
• Few-Shot Pattern Detection via Template Matching and Regression
• Weights-Rotated Preference Optimization for Large Language Models
• Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection
• Consistent Opponent Modeling of Static Opponents in Imperfect-Information Games
• Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
• Robustness Feature Adapter for Efficient Adversarial Training
• Unlearning as Ablation: Toward a Falsifiable Benchmark for Generative Scientific Discovery
• Database Normalization via Dual-LLM Self-Refinement
• Instant Preference Alignment for Text-to-Image Diffusion Models
• Speculative Safety-Aware Decoding
• EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation of EEG Foundation Models
• Talking to Robots: A Practical Examination of Speech Foundation Models for HRI Applications
• DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou
• Algebraic Approach to Ridge-Regularized Mean Squared Error Minimization in Minimal ReLU Neural Network
• Proximal Supervised Fine-Tuning
• Adaptive Output Steps: FlexiSteps Network for Dynamic Trajectory Prediction
• MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
• Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture
• UniSino: Physics-Driven Foundational Model for Universal CT Sinogram Standardization
• Limitations of Normalization in Attention Mechanism
• Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio
• Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning in LLMs
• VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
• AVAM: Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering
• Ada-TransGNN: An Air Quality Prediction Model Based On Adaptive Graph Convolutional Networks
• FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
• Vocoder-Projected Feature Discriminator
• Edge-Enhanced Vision Transformer Framework for Accurate AI-Generated Image Detection
• Designing Practical Models for Isolated Word Visual Speech Recognition
• A Defect Classification Framework for AI-Based Software Systems (AI-ODC)
• Riemannian Optimization for LoRA on the Stiefel Manifold
• AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation
• See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops
• A Feminist Account of Intersectional Algorithmic Fairness
• Debiasing Multilingual LLMs in Cross-lingual Latent Space
• Understanding Subword Compositionality of Large Language Models
• Automating Conflict-Aware ACL Configurations with Natural Language Intents
• Previously on... Automating Code Review
• Towards Continual Visual Anomaly Detection in the Medical Domain
• AQ-PCDSys: An Adaptive Quantized Planetary Crater Detection System for Autonomous Space Exploration
• HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data
• Dynamic Fusion Multimodal Network for SpeechWellness Detection
• Arnold: a generalist muscle transformer policy
• Named Entity Recognition of Historical Text via Large Language Model
• A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code
• CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics
• Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations
• Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation
• Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability
• The Computational Complexity of Satisfiability in State Space Models
• Amortized Sampling with Transferable Normalizing Flows
• AdLoCo: adaptive batching significantly improves communications efficiency and convergence for Large Language Models
• A biological vision inspired framework for machine perception of abutting grating illusory contours
• Provable Generalization in Overparameterized Neural Nets
• ResLink: A Novel Deep Learning Architecture for Brain Tumor Classification with Area Attention and Residual Connections
• Deep Learning-Assisted Detection of Sarcopenia in Cross-Sectional Computed Tomography Imaging
• Explain Before You Answer: A Survey on Compositional Visual Reasoning
• Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
• Chinese Court Simulation with LLM-Based Agent System
• CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation
• Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering
• Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMs
• Modality-Specific Speech Enhancement and Noise-Adaptive Fusion for Acoustic and Body-Conduction Microphone Framework
• Capturing Legal Reasoning Paths from Facts to Law in Court Judgments using Knowledge Graphs
• Agentic AI for Software: thoughts from Software Engineering community
• The Arabic Generality Score: Another Dimension of Modeling Arabic Dialectness
• Condition Weaving Meets Expert Modulation: Towards Universal and Controllable Image Generation
• Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
• Neural Proteomics Fields for Super-resolved Spatial Proteomics Prediction
• Physics-Inspired Spatial Temporal Graph Neural Networks for Predicting Industrial Chain Resilience
• A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems
• NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
• Gaussian Primitive Optimized Deformable Retinal Image Registration
• DevLicOps: A Framework for Mitigating Licensing Risks in AI-Generated Code
• A Workflow for Map Creation in Autonomous Vehicle Simulations
• WildSpoof Challenge Evaluation Plan
• TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings
• Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling
• Tri-Accel: Curvature-Aware Precision-Adaptive and Memory-Elastic Optimization for Efficient GPU Usage
• TextOnly: A Unified Function Portal for Text-Related Functions on Smartphones
• Degree of Staleness-Aware Data Updating in Federated Learning
• THEME : Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics
• HumanoidVerse: A Versatile Humanoid for Vision-Language Guided Multi-Object Rearrangement
• Drive As You Like: Strategy-Level Motion Planning Based on A Multi-Head Diffusion Model
• Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
• LLM-based Human-like Traffic Simulation for Self-driving Tests
• Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective
• Combating Digitally Altered Images: Deepfake Detection
• ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation
• Score Matching on Large Geometric Graphs for Cosmology Generation
• GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation
• An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation
• TabResFlow: A Normalizing Spline Flow Model for Probabilistic Univariate Tabular Regression
• SSG-Dit: A Spatial Signal Guided Framework for Controllable Video Generation
• Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration
• Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages
• Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation
• Proximal Vision Transformer: Enhancing Feature Representation through Two-Stage Manifold Geometry
• Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings
• Convolutional Neural Networks for Accurate Measurement of Train Speed
• Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
• PlantVillageVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science
• Token Homogenization under Positional Bias
• CE-RS-SBCIT A Novel Channel Enhanced Hybrid CNN Transformer with Residual, Spatial, and Boundary-Aware Learning for Brain Tumor MRI Analysis
• SACA: Selective Attention-Based Clustering Algorithm
• Natural Language Satisfiability: Exploring the Problem Distribution and Evaluating Transformer-based Language Models
• Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
• Beyond Play and Pause: Turning GPT-4o Spatial Weakness into a Strength for In-Depth Interactive Video Learning
• Error analysis for the deep Kolmogorov method
• ONG: Orthogonal Natural Gradient Descent
• Scaling Graph Transformers: A Comparative Study of Sparse and Dense Attention
• LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components
• BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
• Multi-Agent Visual-Language Reasoning for Comprehensive Highway Scene Understanding
• How to make Medical AI Systems safer? Simulating Vulnerabilities, and Threats in Multimodal Medical RAG System
• GPG-HT: Generalized Policy Gradient with History-Aware Decision Transformer for Probabilistic Path Planning
• Exposing Privacy Risks in Graph Retrieval-Augmented Generation
• SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
• Multi-Metric Preference Alignment for Generative Speech Restoration
• Module-Aware Parameter-Efficient Machine Unlearning on Transformers
• ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation
• CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
• Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding
• PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration
• Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization
• The AI Data Scientist
• SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
• ST-Raptor: LLM-Powered Semi-Structured Table Question Answering
• Unraveling the cognitive patterns of Large Language Models through module communities
• Disentangling the Factors of Convergence between Brains and Computer Vision Models
• Efficient Computation of Blackwell Optimal Policies using Rational Functions
• Hermes 4 Technical Report
• Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II
• Predicting User Grasp Intentions in Virtual Reality
• Robust Market Making: To Quote, or not To Quote
• ARL-Based Multi-Action Market Making with Hawkes Processes and Variable Volatility
• Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
• Humans Perceive Wrong Narratives from AI Reasoning Texts
• An Embodied AR Navigation Agent: Integrating BIM with Retrieval-Augmented Generation for Language Guidance
• GreenTEA: Gradient Descent with Topic-modeling and Evolutionary Auto-prompting
• Multimodal Appearance based Gaze-Controlled Virtual Keyboard with Synchronous Asynchronous Interaction for Low-Resource Settings
• "Accessibility people, you go work on that thing of yours over there": Addressing Disability Inclusion in AI Product Organizations
• Social Identity in Human-Agent Interaction: A Primer
• To Explain Or Not To Explain: An Empirical Investigation Of AI-Based Recommendations On Social Media Platforms
• Negative Shanshui: Real-time Interactive Ink Painting Synthesis
• STRelay: A Universal Spatio-Temporal Relaying Framework for Location Prediction with Future Spatiotemporal Contexts
• A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction
• The GPT-4o Shock Emotional Attachment to AI Models and Its Impact on Regulatory Acceptance: A Cross-Cultural Analysis of the Immediate Transition from GPT-4o to GPT-5
• Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection
• The Impact of Artificial Intelligence on Human Thought
• Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
• Adaptive Variance-Penalized Continual Learning with Fisher Regularization
• Few-shot Class-incremental Fault Diagnosis by Preserving Class-Agnostic Knowledge with Dual-Granularity Representations
• Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow
• From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective
• Equinox: Holistic Fair Scheduling in Serving Large Language Models
• LatentFlow: Cross-Frequency Experimental Flow Reconstruction from Sparse Pressure via Latent Mapping
• HiCL: Hippocampal-Inspired Continual Learning
• Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
• Optimizing Hyper parameters in CNN for Soil Classification using PSO and Whale Optimization Algorithm
• The Loupe: A Plug-and-Play Attention Module for Amplifying Discriminative Features in Vision Transformers
• Trust but Verify! A Survey on Verification Design for Test-time Scaling
• Situational Awareness as the Imperative Capability for Disaster Resilience in the Era of Complex Hazards and Artificial Intelligence
• COVID19 Prediction Based On CT Scans Of Lungs Using DenseNet Architecture
• Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification
• The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms
• Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
• MedRepBench: A Comprehensive Benchmark for Medical Report Interpretation
• Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration
• CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression
• STGAtt: A Spatial-Temporal Unified Graph Attention Network for Traffic Flow Forecasting
• Cybernaut: Towards Reliable Web Automation
• Making AI Inevitable: Historical Perspective and the Problems of Predicting Long-Term Technological Change
• Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
• DecoMind: A Generative AI System for Personalized Interior Design Layouts
• QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting
• GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model
• Generative Artificial Intelligence and Agents in Research and Teaching
• Dynamic Sparse Attention on Mobile SoCs
• Assessing Consciousness-Related Behaviors in Large Language Models Using the Maze Test
• RoboBuddy in the Classroom: Exploring LLM-Powered Social Robots for Storytelling in Learning and Integration Activities
• Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
• CelloAI: Leveraging Large Language Models for HPC Software Development in High Energy Physics
• AI Product Value Assessment Model: An Interdisciplinary Integration Based on Information Theory, Economics, and Psychology
• WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning
• CellEcoNet: Decoding the Cellular Language of Pathology with Deep Learning for Invasive Lung Adenocarcinoma Recurrence Prediction
• Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
• FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction
• Guarding Your Conversations: Privacy Gatekeepers for Secure Interactions with Cloud-Based AI Models
• EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention
• Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data
• Interpreting the Effects of Quantization on LLMs
• Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach
• Exploring the Impact of Generative Artificial Intelligence on Software Development in the IT Sector: Preliminary Findings on Productivity, Efficiency and Job Security
• Understanding and Tackling Over-Dilution in Graph Neural Networks
• Out of Distribution Detection for Efficient Continual Learning in Quality Prediction for Arc Welding
• Revisiting Rule-Based Stuttering Detection: A Comprehensive Analysis of Interpretable Models for Clinical Applications
• Explainable AI for Predicting and Understanding Mathematics Achievement: A Cross-National Analysis of PISA 2018
• Evaluation and LLM-Guided Learning of ICD Coding Rationales
• PuzzleJAX: A Benchmark for Reasoning and Learning
• Route-and-Execute: Auditable Model-Card Matching and Specialty-Level Deployment
• Quantifying Sycophancy as Deviations from Bayesian Rationality in LLMs
• RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis
• Complexity in finitary argumentation (extended version)
• WebSight: A Vision-First Architecture for Robust Web Agents
• Solving the Min-Max Multiple Traveling Salesmen Problem via Learning-Based Path Generation and Optimal Splitting
• PowerChain: Automating Distribution Grid Analysis with Agentic AI Workflows
• Rethinking How AI Embeds and Adapts to Human Values: Challenges and Opportunities
• MaRVL-QA: A Benchmark for Mathematical Reasoning over Visual Landscapes
• PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
• From reactive to cognitive: brain-inspired spatial intelligence for embodied agents
• Large Language Model-Based Automatic Formulation for Stochastic Optimization Models
• Explainable Counterfactual Reasoning in Depression Medication Selection at Multi-Levels (Personalized and Population)
• Reinforcement Learning enhanced Online Adaptive Clinical Decision Support via Digital Twin powered Policy and Treatment Effect optimized Reward
• MC3G: Model Agnostic Causally Constrained Counterfactual Generation
• L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems
• Federated Reinforcement Learning for Runtime Optimization of AI Applications in Smart Eyewears
• ERF-BA-TFD+: A Multimodal Model for Audio-Visual Deepfake Detection
• MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment
• Meta-R1: Empowering Large Reasoning Models with Metacognition
• Evolving Collective Cognition in Human-Agent Hybrid Societies: How Agents Form Stances and Boundaries
• Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery
• Large Language Models as Universal Predictors? An Empirical Study on Small Tabular Datasets
• Solving Constrained Stochastic Shortest Path Problems with Scalarisation
• School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
• Evaluating Retrieval-Augmented Generation Strategies for Large Language Models in Travel Mode Choice Prediction
• Consciousness as a Functor
• TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis
• Evaluating Movement Initiation Timing in Ultimate Frisbee via Temporal Counterfactuals
• Spacer: Towards Engineered Scientific Inspiration
• A Taxonomy of Transcendence
• LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
• AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks
• Interpretable Early Failure Detection via Machine Learning and Trace Checking-based Monitoring
• FAIRGAMER: Evaluating Biases in the Application of Large Language Models to Video Games
• Language Models Coupled with Metacognition Can Outperform Reasoning Models