mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 19 Nov 2025

305 papers

  1. Enhancing Reliability across Short and Long-Form QA via Reinforcement LearningLLM reasoning → Hallucination detection and mitigation +1
  2. Noise-Robust Abstractive Compression in Retrieval-Augmented Language ModelsRetrieval-augmented generation → Generation and context integration
  3. The Specification Trap: Why Static Value Alignment Alone Is Insufficient for Robust AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  4. Entropy-Based Measurement of Value Drift and Alignment Work in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  5. When Harmless Words Harm: A New Threat to LLM Safety via Conceptual TriggersLLM safety and security → Jailbreaking
  6. CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict ResolutionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  7. Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov ProjectionDiffusion models → Diffusion foundations and sampling
  8. Can we use LLMs to bootstrap reinforcement learning? -- A case study in digital health behavior changeSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  9. A Coq-based Axiomatization of Tarski's MereogeometryLLM reasoning → Spatial and embodied reasoning
  10. DiffuMamba: High-Throughput Diffusion LMs with Mamba BackboneDiffusion models → Discrete and text diffusion +2
  11. RB-FT: Rationale-Bootstrapped Fine-Tuning for Video ClassificationMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  12. Thinking, Faithful and Stable: Mitigating Hallucinations in LLMsLLM reasoning → Hallucination detection and mitigation
  13. AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel OptimizationLLM agents and tool use → Software engineering coding agents +1
  14. Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex MinimizationEfficient LLM inference and serving → Speculative decoding
  15. Decomposing Theory of Mind: How Emotional Processing Mediates ToM Abilities in LLMsMechanistic interpretability → Activation steering methods
  16. What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  17. The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  18. Step-Audio-R1 Technical ReportLLM reasoning → Audio-language model reasoning
  19. TB or Not TB: Coverage-Driven Direct Preference Optimization for Verilog Stimulus GenerationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  20. Securing AI Agents Against Prompt Injection AttacksRetrieval-augmented generation → Privacy and security of RAG +2
  21. Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident ResponseLLM agents and tool use → General LLM agent frameworks and benchmarks
  22. Build AI Assistants using Large Language Models and Agents to Enhance the Engineering Education of BiomechanicsLLM agents and tool use → Educational agents and math problem solving
  23. GeoVista: Web-Augmented Agentic Visual Reasoning for GeolocalizationLLM reasoning → Spatial and embodied reasoning +1
  24. The Impact of Quantization on Large Reasoning Model Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  25. MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert SkippingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  26. VisPlay: Self-Evolving Vision-Language Models from ImagesLLM reasoning → Multimodal reasoning +2
  27. Continual Reinforcement Learning for Cyber-Physical Systems: Lessons Learned and Open ChallengesDeep reinforcement learning methods → Deep RL algorithms and representations
  28. When to Think and When to Look: Uncertainty-Guided LookbackLLM reasoning → Multimodal reasoning +1
  29. SRPO: Self-Referential Policy Optimization for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
  30. What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation DiversityLLM agents and tool use → Web, search, and research agents
  31. AVATAAR: Agentic Video Answering via Temporal Adaptive Alignment and ReasoningLLM reasoning → Multimodal reasoning +1
  32. HSKBenchmark: Modeling and Benchmarking Chinese Second Language Acquisition in Large Language Models through Curriculum TuningMechanistic interpretability → Knowledge and representations inside LLMs
  33. From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision TransformersMechanistic interpretability → Interpreting vision and multimodal models +1
  34. Computer-Use Agents as Judges for Generative User InterfaceLLM agents and tool use → GUI and mobile agents
  35. Multimodal Evaluation of Russian-language ArchitecturesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  36. Theoretical Closed-loop Stability Bounds for Dynamical System Coupled with Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  37. Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent MiningLLM agents and tool use → Financial trading and forecasting agents
  38. HV-Attack: Hierarchical Visual Attack for Multimodal Retrieval Augmented GenerationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  39. IPR-1: Interactive Physical ReasonerWorld models → Latent predictive world models
  40. DEPO: Dual-Efficiency Preference Optimization for LLM AgentsLLM reasoning → Reinforcement learning for reasoning +2
  41. Terra Nova: A Comprehensive Challenge Environment for Intelligent AgentsDeep reinforcement learning methods → RL training of language and agent models
  42. Parameter Importance-Driven Continual Learning for Foundation ModelsLLM reasoning → Multimodal reasoning
  43. Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph AttentionDeep reinforcement learning methods → Safe and constrained RL
  44. HEAD-QA v2: Expanding a Healthcare Benchmark for ReasoningLLM reasoning → Clinical and biomedical applications
  45. Octopus: Agentic Multimodal Reasoning with Six-Capability OrchestrationLLM reasoning → Multimodal reasoning +1
  46. C2F-Space: Coarse-to-Fine Space Grounding for Spatial Instructions using Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  47. DesignerlyLoop: Forming Design Intent through Curated Reasoning for Human-LLM AlignmentLLM reasoning → Reasoning benchmarks and evaluation +1
  48. Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  49. Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language ModelsLLM safety and security → Jailbreaking
  50. Reinforcement Learning in Queue-Reactive Models: Application to Optimal ExecutionDeep reinforcement learning methods → Adversarial robustness and RL in finance
  51. GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  52. Trustworthy and Fair SkinGPT-R1 for Democratizing Dermatological Reasoning across Diverse EthnicitiesLLM reasoning → Clinical and biomedical applications
  53. Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative StoryMechanistic interpretability → SAE features and their applications
  54. Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion ZonesLLM reasoning → Diffusion reasoning and test-time scaling
  55. Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense FrameworksLLM agents and tool use → Agent threats, guardrails and governance +1
  56. Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary MultitaskingDeep reinforcement learning methods → Deep RL algorithms and representations
  57. Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement LearningDiffusion models → Discrete and text diffusion +1
  58. Vehicle Routing Problems via Quantum Graph Attention Network Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  59. FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion ModelDiffusion models → Flow matching, time series and science
  60. Adaptive Inverse Reinforcement Learning with Online Off-Policy Data CollectionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  61. SafeRBench: Dissecting the Reasoning Safety of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  62. Multimodal Continual Instruction Tuning with Dynamic Gradient GuidanceMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  63. ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based RecommendationLLM reasoning → LLM reasoning for recommendation +1
  64. From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMsLLM reasoning → Reinforcement learning for reasoning
  65. Effective Code Membership Inference for Code Completion Models via Adversarial PromptsLLM safety and security → Membership inference attacks
  66. A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +2
  67. MAIF: Enforcing AI Trust and Provenance with an Artifact-Centric Agentic ParadigmLLM agents and tool use → Agent threats, guardrails and governance
  68. Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image SynthesisDiffusion models → 3D, point cloud and scene generation
  69. SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and ReasoningLLM reasoning → Multimodal reasoning
  70. Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly DetectionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  71. MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal VariationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  72. Knowledge-Informed Automatic Feature Extraction via Collaborative Large Language Model AgentsLLM agents and tool use → Web, search, and research agents
  73. ProRAC: A Neuro-symbolic Method for Reasoning about Actions with LLM-based ProgressionLLM reasoning → Reasoning benchmarks and evaluation
  74. BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow MatchingDiffusion models → 3D, point cloud and scene generation
  75. Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving TasksLLM reasoning → Multimodal reasoning
  76. Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question AnsweringLLM agents and tool use → Medical and scientific domain agents
  77. Evaluating Multimodal Large Language Models on Vertically Written Japanese TextMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  78. Aligning Generative Music AI with Human Preferences: Methods and ChallengesLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  79. Dynamic Expert Quantization for Scalable Mixture-of-Experts InferenceMixture-of-experts → Efficient MoE training and inference systems
  80. FinCriticalED: A Visual Benchmark for Financial Fact-Level OCRMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  81. SoK: Critical Evaluation of Quantum Machine Learning for Adversarial RobustnessLLM safety and security → Machine unlearning
  82. An Alignment-Based Approach to Learning Motions from DemonstrationsOffline RL and imitation learning from data → Robot learning from demonstration
  83. C2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models
  84. Pharmacophore-based design by learning on voxel grids
  85. Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A
  86. Seizure-NGCLNet: Representation Learning of SEEG Spatial Pathological Patterns for Epileptic Seizure Detection via Node-Graph Dual Contrastive Learning
  87. Coarse-to-Fine Non-Rigid Registration for Side-Scan Sonar Mosaicking
  88. German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
  89. PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health Organizations
  90. An Optimized Machine Learning Classifier for Detecting Fake Reviews Using Extracted Features
  91. TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin
  92. Model-to-Model Knowledge Transmission (M2KT): A Data-Free Framework for Cross-Model Understanding Transfer
  93. PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
  94. TSRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detection
  95. Upstream Probabilistic Meta-Imputation for Multimodal Pediatric Pancreatitis Classification
  96. BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?
  97. Smart Manufacturing: MLOps-Enabled Event-Driven Architecture for Enhanced Control in Steel Production
  98. Enhanced Federated Deep Multi-View Clustering under Uncertainty Scenario
  99. Boundary-Aware Adversarial Filtering for Reliable Diagnosis under Extreme Class Imbalance
  100. Rectifying Distribution Shift in Cascaded Precipitation Nowcasting
All 305
  1. Unified all-atom molecule generation with neural fields
  2. Bayesian Semiparametric Causal Inference: Targeted Doubly Robust Estimation of Treatment Effects
  3. EEG Emotion Recognition Through Deep Learning
  4. Cross-Balancing for Data-Informed Design and Efficient Analysis of Observational Studies
  5. Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language
  6. AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulation
  7. Automatic Uncertainty-Aware Synthetic Data Bootstrapping for Historical Map Segmentation
  8. WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion
  9. AquaSentinel: Next-Generation AI System Integrating Sensor Networks for Urban Underground Water Pipeline Anomaly Detection via Collaborative MoE-LLM Agent Architecture
  10. A Crowdsourced Study of ChatBot Influence in Value-Driven Decision Making Scenarios
  11. GLOBE: Accurate and Generalizable PDE Surrogates using Domain-Inspired Architectures and Equivariances
  12. discretize_distributions: Efficient Quantization of Gaussian Mixtures with Guarantees in Wasserstein Distance
  13. The Ensemble Kalman Inversion Race
  14. Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution
  15. The Loss of Control Playbook: Degrees, Dynamics, and Preparedness
  16. Attention-Based Feature Online Conformal Prediction for Time Series
  17. EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3
  18. UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
  19. Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions
  20. IMACT-CXR: An Interactive Multi-Agent Conversational Tutoring System for Chest X-Ray Interpretation
  21. Atlas Gaussian processes on restricted domains and point clouds
  22. Beyond Tsybakov: Model Margin Noise and H-Consistency Bounds
  23. Multidimensional scaling of two-mode three-way asymmetric dissimilarities: finding archetypal profiles and clustering
  24. TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models
  25. SURFing to the Fundamental Limit of Jet Tagging
  26. Balancing Natural Language Processing Accuracy and Normalisation in Extracting Medical Insights
  27. UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation
  28. Identifying the Supply Chain of AI for Trustworthiness and Risk Management in Critical Applications
  29. A time for monsters: Organizational knowing after LLMs
  30. Writing With Machines and Peers: Designing for Critical Engagement with Generative AI
  31. Tokenisation over Bounded Alphabets is Hard
  32. RoMa v2: Harder Better Faster Denser Feature Matching
  33. In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
  34. Think Visually, Reason Textually: Vision-Language Synergy in ARC
  35. First Frame Is the Place to Go for Video Content Customization
  36. Joint Semantic-Channel Coding and Modulation for Token Communications
  37. RescueLens: LLM-Powered Triage and Action on Volunteer Feedback for Food Rescue
  38. Hyperspectral Image Classification using Spectral-Spatial Mixer Network
  39. Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
  40. Front-door Reducibility: Reducing ADMGs to the Standard Front-door Setting via a Graphical Criterion
  41. MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features
  42. GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
  43. INQUIRE-Search: Interactive Discovery in Large-Scale Biodiversity Databases
  44. FDIO: Frequency Decomposed Inertial Odometry
  45. Multi-Stage Residual-Aware Unsupervised Deep Learning Framework for Consistent Ultrasound Strain Elastography
  46. R'enyi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincar'e Inequalities
  47. Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
  48. CODE-II: A large-scale dataset for artificial intelligence in ECG analysis
  49. Sufficient Explanations in Databases and their Connections to Database Repairs
  50. The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification
  51. CODE: A global approach to ODE dynamics learning
  52. FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
  53. Near-optimal Delta-convex Estimation of Lipschitz Functions
  54. Optimus-Q: Utilizing Federated Learning in Adaptive Robots for Intelligent Nuclear Power Plant Operations through Quantum Cryptography
  55. MaskMed: Decoupled Mask and Class Prediction for Medical Image Segmentation
  56. US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recovery
  57. Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognition
  58. MHR: Momentum Human Rig
  59. CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking
  60. Transferable Dual-Domain Feature Importance Attack against AI-Generated Image Detector
  61. Scriboora: Rethinking Human Pose Forecasting
  62. B+ANN: A Fast Billion-Scale Disk-based Nearest-Neighbor Index
  63. A Physics Informed Machine Learning Framework for Optimal Sensor Placement and Parameter Estimation
  64. A Hybrid CNN-ViT-GNN Framework with GAN-Based Augmentation for Intelligent Weed Detection in Precision Agriculture
  65. Exploring the use of AI authors and reviewers at Agents4Science
  66. Convergence and Sketching-Based Efficient Computation of Neural Tangent Kernel Weights in Physics-Based Loss
  67. Decentralized Gaussian Process Classification and an Application in Subsea Robotics
  68. PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles
  69. Multi-Text Guided Few-Shot Semantic Segmentation
  70. Standardising the NLP Workflow: A Framework for Reproducible Linguistic Analysis
  71. Sample-Adaptivity Tradeoff in On-Demand Sampling
  72. DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures
  73. Learning to Expand Images for Efficient Visual Autoregressive Modeling
  74. Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels
  75. NTK-Guided Implicit Neural Teaching
  76. A Novel CustNetGC Boosted Model with Spectral Features for Parkinson's Disease Prediction
  77. FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
  78. RS-CA-HSICT: A Residual and Spatial Channel Augmented CNN Transformer Framework for Monkeypox Detection
  79. Deep Learning for Accurate Vision-based Catch Composition in Tropical Tuna Purse Seiners
  80. SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome
  81. Insights from the ICLR Peer Review and Rebuttal Process
  82. Driving in Spikes: An Entropy-Guided Object Detector for Spike Cameras
  83. FairEnergy: Contribution-Based Fairness meets Energy Efficiency in Federated Learning
  84. TSFM in-context learning for time-series classification of bearing-health status
  85. Gini Score under Ties and Case Weights
  86. Neural network-driven domain decomposition for efficient solutions to the Helmholtz equation
  87. CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search
  88. A Dataset and Baseline for Deep Learning-Based Visual Quality Inspection in Remanufacturing
  89. Small Language Models for Phishing Website Detection: Cost, Performance, and Privacy Trade-Offs
  90. Representation Space Constrained Learning with Modality Decoupling for Multimodal Object Detection
  91. Towards Understanding Layer Contributions in Tabular In-Context Learning Models
  92. WarNav: An Autonomous Driving Benchmark for Segmentation of Navigable Zones in War Scenes
  93. LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
  94. Building Robust and Scalable Multilingual ASR for Indian Languages
  95. RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer
  96. D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
  97. Recursive Entropic Variational Inference for Nonlinear State-Space Models
  98. Chinese Short-Form Creative Content Generation via Explanation-Oriented Multi-Objective Optimization
  99. Controlling False Positives in Image Segmentation via Conformal Prediction
  100. ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation
  101. EVA-Net: Interpretable Anomaly Detection for Brain Health via Learning Continuous Aging Prototypes from One-Class EEG Cohorts
  102. Automatic Pruning Discovery for Large Language Models
  103. A Compliance-Preserving Retrieval System for Aircraft MRO Task Search
  104. Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training
  105. CID: Measuring Feature Importance Through Counterfactual Distributions
  106. The Empowerment of Science of Science by Large Language Models: New Tools and Methods
  107. IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers
  108. Cost-Aware Prediction (CAP): An LLM-Enhanced Machine Learning Pipeline and Decision Support System for Heart Failure Mortality Prediction
  109. Multi-layer Stack Ensembles for Time Series Forecasting
  110. Three-Way Open-Set Detection for Robust Autonomous Navigation
  111. Reflexive Evidence-Based Multimodal Learning for Clean Energy Transitions: Causal Insights on Cooking Fuel Access, Urbanization, and Carbon Emissions
  112. STREAM-VAE: Dual-Path Routing for Slow and Fast Dynamics in Vehicle Telemetry Anomaly Detection
  113. Exponential Lasso: robust sparse penalization under heavy-tailed noise and outliers with exponential-type loss
  114. BaGGLS: A Bayesian Shrinkage Framework for Interpretable Modeling of Interactions in High-Dimensional Biological Data
  115. LaguerreNet: Advancing a Unified Solution for Heterophily and Over-smoothing with Adaptive Continuous Polynomials
  116. KrawtchoukNet: A Unified GNN Solution for Heterophily and Over-smoothing with Adaptive Bounded Polynomials
  117. On the Internal Semantics of Time-Series Foundation Models
  118. SkyEgg: Heterogeneity-Aware Hardware Synthesis via Equality Saturation
  119. Adaptive thresholding pattern for fingerprint forgery detection
  120. What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
  121. Robust Bayesian Optimisation with Unbounded Corruptions
  122. A Multimodal Transformer Approach for UAV Detection and Aerial Object Recognition Using Radar, Audio, and Video Data
  123. Text2Loc++: Generalizing 3D Point Cloud Localization from Natural Language
  124. Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs
  125. Taming Generative Synthetic Data for X-ray Prohibited Item Detection
  126. MAPROC at AHaSIS Shared Task: Few-Shot and Sentence Transformer for Sentiment Analysis of Arabic Hotel Reviews
  127. Edge-Centric Relational Reasoning for 3D Scene Graph Prediction
  128. Path Planning through Multi-Agent Reinforcement Learning in Dynamic Environments
  129. Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research
  130. Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception
  131. SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
  132. Behavior Trees vs Executable Ontologies: a Comparative Analysis of Robot Control Paradigms
  133. Graph Query Networks for Object Detection with Automotive Radar
  134. ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing
  135. IndicGEC: Powerful Models, or a Measurement Mirage?
  136. Efficiency Will Not Lead to Sustainable Reasoning AI
  137. SplitFlux: Learning to Decouple Content and Style from a Single Image
  138. M, Toolchain and Language for Reusable Model Compilation
  139. PresentCoach: Dual-Agent Presentation Coaching through Exemplars and Interactive Feedback
  140. PLATONT: Learning a Platonic Representation for Unified Network Tomography
  141. Optimized scheduling of electricity-heat cooperative system considering wind energy consumption and peak shaving and valley filling
  142. EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
  143. D2D Power Allocation via Quantum Graph Neural Network
  144. Context Cascade Compression: Exploring the Upper Limits of Text Compression
  145. Why Physics Still Matters: Improving Machine Learning Prediction of Material Properties with Phonon-Informed Datasets
  146. OEMA: Ontology-Enhanced Multi-Agent Collaboration Framework for Zero-Shot Clinical Named Entity Recognition
  147. Physics-Based Benchmarking Metrics for Multimodal Synthetic Images
  148. SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making
  149. Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval
  150. Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition
  151. Particle Monte Carlo methods for Lattice Field Theory
  152. Eq.Bot: Enhance Robotic Manipulation Learning via Group Equivariant Canonicalization
  153. As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Files
  154. HISE-KT: Synergizing Heterogeneous Information Networks and LLMs for Explainable Knowledge Tracing with Meta-Path Optimization
  155. BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI
  156. Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset
  157. HinTel-AlignBench: A Framework and Benchmark for Hindi-Telugu with English-Aligned Samples
  158. SWR-Viz: AI-assisted Interactive Visual Analytics Framework for Ship Weather Routing
  159. MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction
  160. Data-driven Prediction of Species-Specific Plant Responses to Spectral-Shifting Films from Leaf Phenotypic and Photosynthetic Traits
  161. Complex variational autoencoders admit K"ahler structure
  162. Finetuning LLMs for Automatic Form Interaction on Web-Browser in Selenium Testing Framework
  163. Learning Depth from Past Selves: Self-Evolution Contrast for Robust Depth Estimation
  164. Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments
  165. Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs
  166. Multimodal Wireless Foundation Models
  167. Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation
  168. SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection
  169. DCL-SE: Dynamic Curriculum Learning for Spatiotemporal Encoding of Brain Imaging
  170. Beyond Uncertainty Sets: Leveraging Optimal Transport to Extend Conformal Predictive Distributions to Multivariate Settings
  171. CASPER: Cross-modal Alignment of Spatial and single-cell Profiles for Expression Recovery
  172. Cross-Modal Consistency-Guided Active Learning for Affective BCI Systems
  173. Novel sparse matrix algorithm expands the feasible size of a self-organizing map of the knowledge indexed by a database of peer-reviewed medical literature
  174. WaveFuse-AL: Cyclical and Performance-Adaptive Multi-Strategy Active Learning for Medical Images
  175. CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries
  176. Efficient RF Passive Components Modeling with Bayesian Online Learning and Uncertainty Aware Sampling
  177. Multi-Aspect Cross-modal Quantization for Generative Recommendation
  178. Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
  179. Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation
  180. An Event-triggered System for Social Persuasion and Danger Alert in Elder Home Monitoring
  181. Semiconductor Industry Trend Prediction with Event Intervention Based on LSTM Model in Sentiment-Enhanced Time Series Data
  182. Eye Care You: Voice Guidance Application Using Social Robot for Visually Impaired People
  183. Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting
  184. TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition
  185. GPU-Initiated Networking for NCCL
  186. Classification Trees with Valid Inference via the Exponential Mechanism
  187. Deep Pathomic Learning Defines Prognostic Subtypes and Molecular Drivers in Colorectal Cancer
  188. Interpretable temporal fusion network of multi- and multi-class arrhythmia classification
  189. Transformed ℓ1 Gradient Regularization for Image Denoising
  190. ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling
  191. Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
  192. CellGenNet: A Knowledge-Distilled Framework for Robust Cell Segmentation in Cancer Tissues
  193. Hyperspectral Super-Resolution with Inter-Image Variability via Degradation-based Low-Rank and Residual Fusion Method
  194. Oversampling techniques for predicting COVID-19 patient length of stay
  195. UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space
  196. Simulated Human Learning in a Dynamic, Partially-Observed, Time-Series Environment
  197. Computer Vision Modeling of the Development of Geometric and Numerical Concepts in Humans
  198. Complex-Valued 2D Gaussian Representation for Computer-Generated Holography
  199. CKDA: Cross-modality Knowledge Disentanglement and Alignment for Visible-Infrared Lifelong Person Re-identification
  200. Latent space analysis and generalization to out-of-distribution data
  201. Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation
  202. IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics
  203. Resource-Based Time and Cost Prediction in Project Networks: From Statistical Modeling to Graph Neural Networks
  204. Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning
  205. Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation