AI Research News Feeds for August 28th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• MTS-Net: Dual-Enhanced Positional Multi-Head Self-Attention for 3D CT Diagnosis of May-Thurner Syndrome
• Analysis and Synthesis Denoisers for Forward-Backward Plug-and-Play Algorithms
• DVM-SLAM: Decentralized Visual Monocular Simultaneous Localization and Mapping for Multi-Agent Systems
• TAGS: 3D Tumor-Adaptive Guidance for SAM
• Personalized MR-Informed Diffusion Models for 3D PET Image Reconstruction
• Deep Learning in Mild Cognitive Impairment Diagnosis using Eye Movements and Image Content in Visual Memory Tasks
• Reduced-Order Modeling of Cyclo-Stationary Time Series Using Score-Based Generative Methods
• Weighted Levenberg-Marquardt methods for fitting multichannel nuclear cross section data
• Eigenvalue distribution of the Neural Tangent Kernel in the quadratic scaling
• Neural Conditional Simulation for Complex Spatial Processes
• Scalable Bayesian Structure Learning for Gaussian Graphical Models Using Marginal Pseudo-likelihood
• The Bayesian Context Trees State Space Model for time series modelling and forecasting
• AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessment
• Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models
• Ego-centric Predictive Model Conditioned on Hand Trajectories
• Self-supervised structured object representation learning
• PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos
• Hyperspectral Sensors and Autonomous Driving: Technologies, Limitations, and Opportunities
• Streamlining the Development of Active Learning Methods in Real-World Object Detection
• Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
• Reimagining Image Segmentation using Active Contour: From Chan Vese Algorithm into a Proposal Novel Functional Loss Framework
• Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
• GS: Generative Segmentation via Label Diffusion
• Segmentation Assisted Incremental Test Time Adaptation in an Open World
• OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations
• PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondence
• Seam360GS: Seamless 360{\deg} Gaussian Splatting from Real-World Omnidirectional Images
• AudioStory: Generating Long-Form Narrative Audio with Large Language Models
• Bridging Domain Gaps for Fine-Grained Moth Classification Through Expert-Informed Adaptation and Foundation Model Priors
• Saccade crossing avoidance as a visual search strategy
• Modeling spectral filtering effects on color-matching functions: Implications for observer variability
• A Technical Review on Comparison and Estimation of Steganographic Tools
• Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents
• DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-View
• Fast Texture Transfer for XR Avatars via Barycentric UV Conversion
• Addressing Deepfake Issue in Selfie banking through camera based authentication
• Context-Aware Risk Estimation in Home Environments: A Probabilistic Framework for Service Robots
• Variational Bayes image restoration with compressive autoencoders
• Latent space configuration for improved generalization in supervised autoencoder neural networks
• REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
• TraceNet: Segment one thing efficiently
• Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis
• DiffArtist: Towards Structure and Appearance Controllable Image Stylization
• ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
• LV-CadeNet: A Long-View Feature Convolution-Attention Fusion Encoder-Decoder Network for EEG/MEG Spike Analysis
• Online Writer Retrieval with Chinese Handwritten Phrases: A Synergistic Temporal-Frequency Representation Learning Approach
• Solving Inverse Problems using Diffusion with Iterative Colored Renoising
• Active Learning for Deep Learning-Based Hemodynamic Parameter Estimation
• End-to-End Action Segmentation Transformer
• Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr\'{e}chet Distance
• OPAL: Visibility-aware LiDAR-to-OpenStreetMap Place Recognition via Adaptive Radial Fusion
• Cross-Modal Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition
• Pixel-Optimization-Free Patch Attack on Stereo Depth Estimation
• LDRFusion: A LiDAR-Dominant multimodal refinement framework for 3D object detection
• PRISM: A Framework Harnessing Unsupervised Visual Representations and Textual Prompts for Explainable MACE Survival Prediction from Cardiac Cine MRI
• EffNetViTLoRA: An Efficient Hybrid Deep Learning Approach for Alzheimer's Disease Diagnosis
• JVLGS: Joint Vision-Language Gas Leak Segmentation
• Weed Detection in Challenging Field Conditions: A Semi-Supervised Framework for Overcoming Shadow Bias and Data Scarcity
• MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment
• CVBench: Evaluating Cross-Video Synergies for Complex Multimodal Understanding and Reasoning
• MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery
• DNP-Guided Contrastive Reconstruction with a Reverse Distillation Transformer for Medical Anomaly Detection
• High-Speed FHD Full-Color Video Computer-Generated Holography
• Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction
• Generalizing Monocular 3D Object Detection
• Quantization Robustness to Input Degradations for Object Detection
• Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model
• UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks
• IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising
• Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models
• Scalable Object Detection in the Car Interior With Vision Foundation Models
• Self-Rewarding Vision-Language Model via Reasoning Decomposition
• Hardware-aware vs. Hardware-agnostic Energy Estimation for SNN in Space Applications
• A Frequency-Aware Self-Supervised Learning for Ultra-Wide-Field Image Enhancement
• SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction
• Synthetic Image Detection via Spectral Gaps of QC-RBIM Nishimori Bethe-Hessian Operators
• LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentation
• FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation
• Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning
• POEv2: a flexible and robust framework for generic line segment detection and wireframe line segment detection
• SPLF-SAM: Self-Prompting Segment Anything Model for Light Field Salient Object Detection
• FastAvatar: Towards Unified Fast High-Fidelity 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers
• BuzzSet v1.0: A Dataset for Pollinator Detection in Field Conditions
• AIM: Adaptive Intra-Network Modulation for Balanced Multimodal Learning
• The Return of Structural Handwritten Mathematical Expression Recognition
• MAPo : Motion-Aware Partitioning of Deformable 3D Gaussian Splatting for High-Fidelity Dynamic Scene Reconstruction
• StableIntrinsic: Detail-preserving One-step Diffusion Model for Multi-view Material Estimation
• Not Every Gift Comes in Gold Paper or with a Red Ribbon: Exploring Color Perception in Text-to-Image Models
• FusionSort: Enhanced Cluttered Waste Segmentation with Advanced Decoding and Comprehensive Modality Optimization
• Context-aware Sparse Spatiotemporal Learning for Event-based Vision
• News is More than a Collection of Facts: Moral Frame Preserving News Summarization
• ICL CIPHERS: Quantifying "Learning" in In-Context Learning via Substitution Ciphers
• Hydra: Structured Cross-Source Enhanced Large Language Model Reasoning
• Refining Czech GEC: Insights from a Multi-Experiment Approach
• PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairs
• Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents
• Reducing Biases towards Minoritized Populations in Medical Curricular Content via Artificial Intelligence for Fairer Health Outcomes
• Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization
• Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
• Do Vision Encoders Truly Explain Object Hallucination?: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore
• Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models
• AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios
• ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
• Selective Retrieval-Augmentation for Long-Tail Legal Text Classification
• Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks
• AraHealthQA 2025 Shared Task Description Paper
• Capabilities of GPT-5 across critical domains: Is it the next breakthrough?
• Beat-Based Rhythm Quantization of MIDI Performances
• Geopolitical Parallax: Beyond Walter Lippmann Just After Large Language Models
• Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking
• Word Chain Generators for Prefix Normal Words
• KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts
• Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
• Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges
• NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
• FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction
• Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
• Agent-as-Judge for Factual Summarization of Long Narratives
• Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
• MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Models
• Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity
• KoWit-24: A Richly Annotated Dataset of Wordplay in News Headlines
• RAGAPHENE: A RAG Annotation Platform with Human Enhancements and Edits
• Leveraging Language Models and Machine Learning in Verbal Autopsy Analysis
• Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
• Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)
• Rule Synergy Analysis using LLMs: State of the Art and Implications
• Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
• Alignment with Fill-In-the-Middle for Enhancing Code Generation
• Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation
• ArgCMV: An Argument Summarization Benchmark for the LLM-era
• Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
• A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection
• Automatic integration of SystemC in the FMI standard for Software-defined Vehicle design
• Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality
• Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
• CAM\~OES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese
• Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
• Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval
• Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
• T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables
• Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
• Scalable and consistent few-shot classification of survey responses using text embeddings
• TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation
• Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning
• Bangla-Bayanno: A 52K-Pair Bengali Visual Question Answering Dataset with LLM-Assisted Translation Refinement
• Your AI Bosses Are Still Prejudiced: The Emergence of Stereotypes in LLM-Based Multi-Agent Systems
• HEAL: A Hypothesis-Based Preference-Aware Analysis Framework
• Online-Score-Aided Federated Learning: Taming the Resource Constraints in Wireless Networks
• Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization
• LLM-based feature generation from text for interpretable machine learning
• Machine Learning for Asymptomatic Ratoon Stunting Disease Detection With Freely Available Satellite Based Multispectral Imaging
• k-HyperEdge Medoids for Clustering Ensemble
• PAC Learnability of Scenario Decision-Making Algorithms: Necessary Conditions and Sufficient Conditions
• Training LLMs with MXFP4
• Human locomotor control timescales depend on the environmental context and sensory input modality
• NAPER: Fault Protection for Real-Time Resource-Constrained Deep Neural Networks
• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
• SubROC: AUC-Based Discovery of Exceptional Subgroup Performance for Binary Classifiers
• Towards a Spatiotemporal Fusion Approach to Precipitation Nowcasting
• Unfolding AlphaFold's Bayesian Roots in Probability Kinematics
• Forecasting Multivariate Urban Data via Decomposition and Spatio-Temporal Graph Analysis
• Computation- and Communication-Efficient Online FL for Resource-Constrained Aerial Vehicles
• Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
• Deep Learning of Semi-Competing Risk Data via a New Neural Expectation-Maximization Algorithm
• Predicting the cardinality and maximum degree of a reduced Gr\"obner basis
• To the Noise and Back: Diffusion for Shared Autonomy
• From Optimization to Control: Quasi Policy Iteration
• Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing
• A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
• Which Spaces can be Embedded in $L_p$-type Reproducing Kernel Banach Space? A Characterization via Metric Entropy
• Robust Detection of Watermarks for Large Language Models Under Human Edits
• On Domain-Adaptive Post-Training for Multimodal Large Language Models
• GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network
• Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers
• TERL: Large-Scale Multi-Target Encirclement Using Transformer-Enhanced Reinforcement Learning
• SuperBPE: Space Travel for Language Models
• Graphical Transformation Models
• Predicting Forced Responses of Probability Distributions via the Fluctuation-Dissipation Theorem and Generative Modeling
• Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
• Multilevel neural simulation-based inference
• mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks
• Hierarchical Decentralized Stochastic Control for Cyber-Physical Systems
• Escaping Stability-Plasticity Dilemma in Online Continual Learning for Motion Forecasting via Synergetic Memory Rehearsal
• Delta-Audit: Explaining What Changes When Models Change
• Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning
• ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation
• SCAR: A Characterization Scheme for Multi-Modal Dataset
• Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables
• $\mathcal{C}^1$-approximation with rational functions and rational neural networks
• Metric spaces of walks and Lipschitz duality on graphs
• Tune My Adam, Please!
• InfraredGP: Efficient Graph Partitioning via Spectral Graph Neural Networks with Negative Corrections
• Fast 3D Diffusion for Scalable Granular Media Synthesis
• Interestingness First Classifiers
• Symplectic convolutional neural networks
• Physics-Informed DeepONet Coupled with FEM for Convective Transport in Porous Media with Sharp Gaussian Sources
• Quantum latent distributions in deep generative models
• Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks
• NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs
• Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning
• GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphs
• Ontology-Based Concept Distillation for Radiology Report Retrieval and Labeling
• FlowletFormer: Network Behavioral Semantic Aware Pre-training Model for Traffic Classification
• Constraint Learning in Multi-Agent Dynamic Games from Demonstrations of Local Nash Interactions
• Global Permutation Entropy
• Short-Horizon Predictive Maintenance of Industrial Pumps Using Time-Series Features and Machine Learning
• Reducing Street Parking Search Time via Smart Assignment Strategies
• Evaluating Language Model Reasoning about Confidential Information
• Self-Supervised Pre-Training with Equilibrium Constraints
• FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring
• Using item recommendations and LLMs in marketing email titles
• Pruning Strategies for Backdoor Defense in LLMs
• Reinforcement Learning for Search Tree Size Minimization in Constraint Programming: New Results on Scheduling Benchmarks
• Large VLM-based Stylized Sports Captioning
• Aggregate Fictitious Play for Learning in Anonymous Polymatrix Games (Extended Version)
• GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification
• Is data-efficient learning feasible with quantum models?
• Stack Trace-Based Crash Deduplication with Transformer Adaptation
• MRExtrap: Longitudinal Aging of Brain MRIs using Linear Modeling in Latent Space
• Towards 6G Intelligence: The Role of Generative AI in Future Wireless Networks
• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models
• A Lightweight Crowd Model for Robot Social Navigation
• Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
• Inferring geometry and material properties from Mueller matrices with machine learning
• Fractal Flow: Hierarchical and Interpretable Normalizing Flow via Topic Modeling and Recursive Strategy
• Fourier Feature Networks for High-Fidelity Prediction of Perturbed Optical Fields
• Benchmarking Hindi LLMs: A New Suite of Datasets and a Comparative Analysis
• Conditional Normalizing Flow Surrogate for Monte Carlo Prediction of Radiative Properties in Nanoparticle-Embedded Layers
• Multimodal Conditional MeshGAN for Personalized Aneurysm Growth Prediction
• TrajFusionNet: Pedestrian Crossing Intention Prediction via Fusion of Sequential and Visual Trajectory Representations
• Sky Background Building of Multi-objective Fiber spectra Based on Mutual Information Network
• On-chip wave chaos for photonic extreme learning
• Experimental End-to-End Optimization of Directly Modulated Laser-based IM/DD Transmission
• 11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis
• Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
• Anomaly Detection in Networked Bandits
• Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
• FraGNNet: A Deep Probabilistic Model for Tandem Mass Spectrum Prediction
• MEraser: An Effective Fingerprint Erasure Approach for Large Language Models
• Analyzing Character Representation in Media Content using Multimodal Foundation Model: Effectiveness and Trust
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
• PyVision: Agentic Vision with Dynamic Tooling
• Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
• Scaling Decentralized Learning with FLock
• MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
• Physics-Informed Regression: Parameter Estimation in Parameter-Linear Nonlinear Dynamic Models
• Memorization in Graph Neural Networks
• Efficient Multi-Source Knowledge Transfer by Model Merging
• Graph Data Modeling: Molecules, Proteins, & Chemical Processes
• Towards Quantum Machine Learning for Malicious Code Analysis
• DETNO: A Diffusion-Enhanced Transformer Neural Operator for Long-Term Traffic Forecasting
• Quantum-Classical Hybrid Molecular Autoencoder for Advancing Classical Decoding
• Kolmogorov-Arnold Representation for Symplectic Learning: Advancing Hamiltonian Neural Networks
• Differentiable multiphase flow model for physics-informed machine learning in reservoir pressure management
• MS-ConTab: Multi-Scale Contrastive Learning of Mutation Signatures for Pan Cancer Representation and Stratification
• Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization
• On Surjectivity of Neural Networks: Can you elicit any behavior from your model?
• The Sample Complexity of Membership Inference and Privacy Auditing
• DeepAtlas: a tool for effective manifold learning
• Distribution Shift Aware Neural Tabular Learning
• MobText-SISA: Efficient Machine Unlearning for Mobility Logs with Spatio-Temporal and Natural-Language Data
• Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning
• Topological Uncertainty for Anomaly Detection in the Neural-network EoS Inference with Neutron Star Data
• Safety Alignment Should Be Made More Than Just A Few Attention Heads
• Attention is also needed for form design
• NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks
• A bag of tricks for real-time Mitotic Figure detection
• Bootstrapping Learned Cost Models with Synthetic SQL Queries
• ERSR: An Ellipse-constrained pseudo-label refinement and symmetric regularization framework for semi-supervised fetal head segmentation in ultrasound images
• From Research to Reality: Feasibility of Gradient Inversion Attacks in Federated Learning
• Gradient Rectification for Robust Calibration under Distribution Shift
• PSO-Merging: Merging Models Based on Particle Swarm Optimization
• SoK: Large Language Model Copyright Auditing via Fingerprinting
• Multispectral LiDAR data for extracting tree points in urban and suburban areas
• Generative AI for Testing of Autonomous Driving Systems: A Survey
• AI-Powered Detection of Inappropriate Language in Medical School Curricula
• The Information Dynamics of Generative Diffusion
• Logical Reasoning with Outcome Reward Models for Test-Time Scaling
• The Next Layer: Augmenting Foundation Models with Structure-Preserving and Attention-Guided Learning for Local Patches to Global Context Awareness in Computational Pathology
• WaveHiT-SR: Hierarchical Wavelet Network for Efficient Image Super-Resolution
• Dhati+: Fine-tuned Large Language Models for Arabic Subjectivity Evaluation
• GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
• Diffusion Language Models Know the Answer Before Decoding
• MathBuddy: A Multimodal System for Affective Math Tutoring
• Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
• Cross-Platform E-Commerce Product Categorization and Recategorization: A Multimodal Hierarchical Classification Approach
• Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
• HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling
• Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence
• Large Language Models (LLMs) for Electronic Design Automation (EDA)
• DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis
• Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices
• Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning
• CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
• From Evidence to Decision: Exploring Evaluative AI
• Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning
• AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation
• Demonstrating specification gaming in reasoning models
• Preference Elicitation for Multi-objective Combinatorial Optimization with Active Learning and Maximum Likelihood Estimation
• Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents
• Fitness Landscape of Large Language Model-Assisted Automated Algorithm Search
• Approximate Lifted Model Construction
• General agents contain world models
• HoneyBee: A Scalable Modular Framework for Creating Multimodal Oncology Datasets with Foundational Embedding Models
• TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes
• Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints
• Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning
• GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
• Understanding Fairness-Accuracy Trade-offs in Machine Learning Models: Does Promoting Fairness Undermine Performance?
• X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models
• PromptKeeper: Safeguarding System Prompts for LLMs
• Score-based Generative Diffusion Models for Social Recommendations
• Statistical learning does not always entail knowledge
• Efficient PINNs via Multi-Head Unimodular Regularization of the Solutions Space
• An Empirical Risk Minimization Approach for Offline Inverse RL and Dynamic Discrete Choice Model
• Constructing a Norm for Children's Scientific Drawing: Distribution Features Based on Semantic Similarity of Large Language Models
• PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis
• Evaluating the Fitness of Ontologies for the Task of Question Generation
• Pricing AI Model Accuracy
• Multi-Type Context-Aware Conversational Recommender Systems via Mixture-of-Experts
• Bidirectional Task-Motion Planning Based on Hierarchical Reinforcement Learning for Strategic Confrontation
• Heat Diffusion Models -- Interpixel Attention Mechanism
• X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
• EnvInjection: Environmental Prompt Injection Attack to Multi-modal Web Agents
• FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing
• BinConv: A Neural Architecture for Ordinal Encoding in Time-Series Forecasting
• Pseudo-Simulation for Autonomous Driving
• DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers
• CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
• Language Models Identify Ambiguities and Exploit Loopholes
• Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference
• Just Because You Can, Doesn't Mean You Should: LLMs for Data Fitting
• Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
• FlowDet: Overcoming Perspective and Scale Challenges in Real-Time End-to-End Traffic Detection
• Energy-Efficient Learning-Based Beamforming for ISAC-Enabled V2X Networks
• Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era
• Multimodal Prototype Alignment for Semi-supervised Pathology Image Segmentation
• Interact-Custom: Customized Human Object Interaction Image Generation
• Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts
• Towards stable AI systems for Evaluating Arabic Pronunciations
• Hallucinating with AI: AI Psychosis as Distributed Delusions
• Complementary Learning System Empowers Online Continual Learning of Vehicle Motion Forecasting in Smart Cities
• CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation
• IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentation
• FinCast: A Foundation Model for Financial Time-Series Forecasting
• LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation
• A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions
• Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
• Training for Obsolescence? The AI-Driven Education Trap
• Divide, Weight, and Route: Difficulty-Aware Optimization with Dynamic Expert Fusion for Long-tailed Recognition
• Invited Paper: Feature-to-Classifier Co-Design for Mixed-Signal Smart Flexible Wearables for Healthcare at the Extreme Edge
• Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception
• Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
• Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation
• Survey of Specialized Large Language Model
• Efficient Model-Based Purification Against Adversarial Attacks for LiDAR Segmentation
• Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
• Object Detection with Multimodal Large Vision-Language Models: An In-depth Review
• DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models
• CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopy
• 2D Ultrasound Elasticity Imaging of Abdominal Aortic Aneurysms Using Deep Neural Networks
• Epistemic Trade-Off: An Analysis of the Operational Breakdown and Ontological Limits of "Certainty-Scope" in AI
• Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities
• Advancements in Crop Analysis through Deep Learning and Explainable AI
• Sistema de Reconocimiento Facial Federado en Conjuntos Abiertos basado en OpenMax
• Are Companies Taking AI Risks Seriously? A Systematic Analysis of Companies' AI Risk Disclosures in SEC 10-K forms
• Automated classification of natural habitats using ground-level imagery
• What Makes AI Applications Acceptable or Unacceptable? A Predictive Moral Framework
• (DEMO) Deep Reinforcement Learning Based Resource Allocation in Distributed IoT Systems
• MedVQA-TREE: A Multimodal Reasoning and Retrieval Framework for Sarcopenia Prediction
• MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation
• An Investigation on Group Query Hallucination Attacks
• AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays
• Deep Data Hiding for ICAO-Compliant Face Images: A Survey
• Quantum Entanglement as Super-Confounding: From Bell's Theorem to Robust Machine Learning
• Re:Frame -- Retrieving Experience From Associative Memory
• Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction
• Atrial Fibrillation Prediction Using a Lightweight Temporal Convolutional and Selective State Space Architecture
• LongReasonArena: A Long Reasoning Benchmark for Large Language Models
• Grounding the Ungrounded: A Spectral-Graph Framework for Quantifying Hallucinations in multimodal LLMs
• Inference of Human-derived Specifications of Object Placement via Demonstration
• Database Entity Recognition with Data Augmentation and Deep Learning
• Fine-Tuning Vision-Language Models for Neutrino Event Analysis in High-Energy Physics Experiments
• One Joke to Rule them All? On the (Im)possibility of Generalizing Humor
• Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention
• A perishable ability? The future of writing in the face of generative artificial intelligence
• Data-Augmented Few-Shot Neural Stencil Emulation for System Identification of Computer Models
• "She was useful, but a bit too optimistic": Augmenting Design with Interactive Virtual Personas
• Bridging Language Gaps: Enhancing Few-Shot Language Adaptation
• Addressing Weak Authentication like RFID, NFC in EVs and EVCs using AI-powered Adaptive Authentication
• Incentivized Lipschitz Bandits
• Inference Gap in Domain Expertise and Machine Intelligence in Named Entity Recognition: Creation of and Insights from a Substance Use-related Dataset
• SIExVulTS: Sensitive Information Exposure Vulnerability Detection System using Transformer Models and Static Analysis
• Automatic Question & Answer Generation Using Generative Large Language Model (LLM)
• Concurrent validity of computer-vision artificial intelligence player tracking software using broadcast footage
• Improving Low-Resource Translation with Dictionary-Guided Fine-Tuning and RL: A Spanish-to-Wayuunaiki Study
• Data-Efficient Symbolic Regression via Foundation Model Distillation
• PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense
• Sat2Flow: A Structure-Aware Diffusion Framework for Human Flow Generation from Satellite Imagery
• Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills
• Learning Game-Playing Agents with Generative Code Optimization
• A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation
• Orchid: Orchestrating Context Across Creative Workflows with Generative AI
• WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
• Sycophancy as compositions of Atomic Psychometric Traits
• Aleks: AI powered Multi Agent System for Autonomous Scientific Discovery via Data-Driven Approaches in Plant Science
• Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs
• Reliable Weak-to-Strong Monitoring of LLM Agents
• SLIM: Subtrajectory-Level Elimination for More Effective Reasoning
• Caught in the Act: a mechanistic approach to detecting deception
• Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
• Skill-based Explanations for Serendipitous Course Recommendation
• ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding
• Instructional Agents: LLM Agents on Automated Course Material Generation for Teaching Faculties
• InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning
• Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
• Tracking World States with Language Models: State-Based Evaluation Using Chess
• CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments
• Flocking Behavior: An Innovative Inspiration for the Optimization of Production Plants
• SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
• Model Science: getting serious about verification, explanation and control of AI systems
• Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices
• MuSpike: A Benchmark and Evaluation Framework for Symbolic Music Generation with Spiking Neural Networks
• Real-Time Intuitive AI Drawing System for Collaboration: Enhancing Human Creativity through Formal and Contextual Intent Integration
• TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models
• Emotional Manipulation by AI Companions
• Lossless Compression of Neural Network Components: Weights, Checkpoints, and K/V Caches in Low-Precision Formats
• A Theory of Information, Variation, and Artificial Intelligence
• The Aegis Protocol: A Foundational Security Framework for Autonomous AI Agents
• MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts
• Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models
• Whisper based Cross-Lingual Phoneme Recognition between Vietnamese and English
• Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT
• MixGAN: A Hybrid Semi-Supervised and Generative Approach for DDoS Detection in Cloud-Integrated IoT Networks
• POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
• Towards Production-Worthy Simulation for Autonomous Cyber Operations
• FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
• CORTEX: Composite Overlay for Risk Tiering and Exposure in Operational AI Systems
• CORE: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning
• RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting
• Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior
• Tricking LLM-Based NPCs into Spilling Secrets
• Seeing Like a Designer Without One: A Study on Unsupervised Slide Quality Assessment via Designer Cue Augmentation