mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 19 Apr 2026

271 papers

  1. Topology-Aware Data Movement for Disaggregated GPU InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  2. Recurrent Reasoning on Symbolic Puzzles with Sequence ModelsLLM reasoning → Test-time compute and efficient thinking
  3. Agentic Social Affordance Framework (ASAF): Agent Identity Design as a Collaboration Interface in Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  4. The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini ModelsLLM safety and security → Safety alignment, refusal and guardrails
  5. Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline MethodsLLM reasoning → Reasoning benchmarks and evaluation
  6. Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for ReasoningLLM reasoning → Reinforcement learning for reasoning
  7. MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE InferenceMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  8. Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU InferenceEfficient LLM inference and serving → KV cache optimization
  9. Lost in Motion: Vision Language Models Fail the Dynamic Gauges TestMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  10. KnowPilot: Your Knowledge-Driven Copilot for Domain TasksLLM agents and tool use → General LLM agent frameworks and benchmarks
  11. Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement LearningSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  12. Towards Self-Improving Error Diagnosis in Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents +1
  13. Poly-EPO: Training Exploratory Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  14. Infrastructure-Centric World Models: Bridging Temporal Depth and Spatial Breadth for Roadside PerceptionWorld models → World models for autonomous driving
  15. ThreadSumm: Summarization of Nested Discourse Threads Using Tree of ThoughtsLLM reasoning → Reasoning benchmarks and evaluation
  16. HCFD: A Benchmark for Audio Deepfake Detection in HealthcareState-space sequence models (S4, Mamba) → Speech and audio SSMs
  17. BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMsMultimodal LLMs / vision-language models → Medical vision-language models
  18. SLO-Guard: Crash-Aware, Budget-Consistent Autotuning for SLO-Constrained LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  19. ViPS: Video-informed Pose Spaces for Auto-Rigged MeshesDiffusion models → Video generation
  20. KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  21. WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy ReasoningLLM reasoning → Reasoning for agents, planning and code
  22. Provable Coordination for LLM Agents via Message Sequence ChartsLLM agents and tool use → General LLM agent frameworks and benchmarks
  23. Agents Explore but Agents Ignore: LLMs Lack Environmental CuriosityLLM agents and tool use → General LLM agent frameworks and benchmarks
  24. DGSSM: Diffusion guided state-space models for multimodal salient object detectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  25. DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENsLLM reasoning → Multimodal reasoning
  26. Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor GenerationLLM reasoning → Reasoning benchmarks and evaluation
  27. Beyond Static Snapshots: A Grounded Evaluation Framework for Language Models at the Agentic FrontierLLM reasoning → Reinforcement learning for reasoning +2
  28. Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System IdentificationDiffusion models → Flow matching, time series and science
  29. SafeAgent: A Runtime Protection Architecture for Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
  30. CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic SearchLLM agents and tool use → Web, search, and research agents
  31. SVL: Goal-Conditioned Reinforcement Learning as Survival LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  32. OPSDL: On-Policy Self-Distillation for Long-Context Language ModelsKnowledge distillation → On-policy and self-distillation for LLMs
  33. Safer Trajectory Planning with CBF-guided Diffusion Model for Unmanned Aerial VehiclesDiffusion models → Diffusion and flow policies for robotics
  34. RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  35. SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph TopologyMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  36. Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMsLLM agents and tool use → Reinforcement learning for LLM agents
  37. CoAct: Co-Active LLM Preference Learning with Human-AI SynergyLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. Coevolving Representations in Joint Image-Feature DiffusionDiffusion models → Diffusion foundations and sampling
  39. AutoVQA-G: Self-Improving Agentic Framework for Automated Visual Question Answering and Grounding AnnotationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +2
  40. Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  41. Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual PerceptionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  42. Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable SpecificationsLLM agents and tool use → Software engineering coding agents
  43. Agentic Education: Using Claude Code to Teach Claude CodeLLM agents and tool use → Software engineering coding agents
  44. Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent CollaborationLLM agents and tool use → Agentic recommender systems
  45. EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and RetrievalRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  46. TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic ControlLLM agents and tool use → Multimodal and embodied agents
  47. Compiling Deterministic Structure into SLM HarnessesLLM reasoning → Reasoning for agents, planning and code
  48. Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  49. Jupiter-N Technical ReportLLM reasoning → Reasoning benchmarks and evaluation
  50. Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  51. ARMove: Learning to Predict Human Mobility through Agentic ReasoningLLM reasoning → Spatial and embodied reasoning +1
  52. Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  53. Think before Go: Hierarchical Reasoning for Image-goal NavigationLLM reasoning → Spatial and embodied reasoning
  54. EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at ScaleLLM agents and tool use → Web, search, and research agents
  55. STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  56. Phase-Scheduled Multi-Agent Systems for Token-Efficient CoordinationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  57. Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  58. Speculative Decoding for Autoregressive Video GenerationDiffusion models → Video generation +1
  59. Representation-Guided Parameter-Efficient LLM UnlearningLLM safety and security → Machine unlearning
  60. SpatialImaginer: Towards Adaptive Visual Imagination for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  61. Towards a Data-Parameter Correspondence for LLMs: A Preliminary DiscussionLLM safety and security → Machine unlearning
  62. When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  63. T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classificationRetrieval-augmented generation → Medical and biomedical RAG
  64. More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic AnchorageMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  65. Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level ScalingLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement LearningRetrieval-augmented generation → Agentic RAG, agents and memory +1
  67. Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample ConstructionDeep reinforcement learning methods → RL training of language and agent models
  68. Signal or Noise in Multi-Agent LLM-based Stock Recommendations?LLM agents and tool use → Financial trading and forecasting agents
  69. Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  70. Towards Joint Quantization and Token Pruning of Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  71. When Background Matters: Breaking Medical Vision Language Models by Transferable AttackMultimodal LLMs / vision-language models → Medical vision-language models
  72. A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and SolutionsLLM reasoning → Reinforcement learning for reasoning
  73. Interpolating Discrete Diffusion Models with Controllable ResamplingDiffusion models → Discrete and text diffusion
  74. Knows: Agent-Native Structured Research RepresentationsLLM agents and tool use → Web, search, and research agents
  75. Efficient Test-Time Scaling via Temporal Reasoning AggregationLLM reasoning → Test-time compute and efficient thinking
  76. RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented GenerationLLM reasoning → Reasoning for agents, planning and code +2
  77. Cat-DPO: Category-Adaptive Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  78. CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency PruningLLM reasoning → Test-time compute and efficient thinking
  79. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to SemanticsLLM reasoning → Time series reasoning
  80. Probabilistic Programs of ThoughtLLM reasoning → Reasoning for agents, planning and code
  81. Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL RepairLLM reasoning → Reasoning for agents, planning and code +1
  82. HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI AgentsLLM agents and tool use → Medical and scientific domain agents
  83. MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical ReasoningLLM reasoning → Clinical and biomedical applications +1
  84. Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  85. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic SearchLLM reasoning → Reasoning for agents, planning and code +1
  86. Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction SteeringLLM reasoning → Audio-language model reasoning
  87. Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  88. Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving SystemsEfficient LLM inference and serving → KV cache optimization
  89. RemoteShield: Enable Robust Multimodal Large Language Models for Earth ObservationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  90. GaLa: Hypergraph-Guided Visual Language Models for Procedural PlanningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  91. HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention HeadsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  92. From Language to Action: Enhancing LLM Task Efficiency with Task-Aware MCP Server RecommendationLLM agents and tool use → Tool learning and function calling
  93. Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLMMultimodal LLMs / vision-language models → Image editing and quality assessment
  94. A Multi-Agent Approach for Claim Verification from Tabular Data DocumentsLLM agents and tool use → Web, search, and research agents
  95. LASER: Low-Rank Activation SVD for Efficient RecursionLLM reasoning → Test-time compute and efficient thinking
  96. Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative ComputationState-space sequence models (S4, Mamba) → Core SSM architectures for language
  97. Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based SimulationLLM agents and tool use → Social simulation and multi-agent debate
  98. Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual ReliabilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  99. Continual Safety Alignment via Gradient-Based Sample SelectionLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  100. Guardrails in Logit Space: Safety Token Regularization for LLM AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
All 271
  1. Demystifying the unreasonable effectiveness of online alignment methodsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  2. DreamShot: Personalized Storyboard Synthesis with Video Diffusion PriorDiffusion models → Video generation
  3. Do LLM-derived graph priors improve multi-agent coordination?LLM agents and tool use → Reinforcement learning for LLM agents
  4. Persona-Based Requirements Engineering for Explainable Multi-Agent Educational Systems: A Scenario Simulator for Clinical Reasoning TrainingLLM agents and tool use → Medical and scientific domain agents
  5. Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork RedundancyMixture-of-experts → Expert routing strategies
  6. LLM Framework for Discovering Major Mathematical Conjectures: AI's Quest for the Next Riemann Hypothesis
  7. AI Tool Discovery at Scale: All You Need is DNS
  8. AI-Driven Analytics of Team-Teaching Talk: Acoustic Patterns across Experience, Cohorts and the Learning Design
  9. Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models
  10. Evaluating Hallucinations in Domain-Adapted Large Language Models
  11. TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
  12. Bidirectional Small-Granularity Search between Code and Text
  13. Human-AI Collaboration for Estimating Scientific Replicability
  14. Evolutionary fine tuning of quantized convolution-based deep learning models
  15. AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G
  16. What Physics do Data-Driven MoCap-to-Radar Models Learn?
  17. Intervention-Aware Multiscale Representation Learning from Imaging Phenomics and Perturbation Transcriptomics
  18. 2D Pre-Training for 3D Pose Estimation
  19. MetaEarth3D: Unlocking World-scale 3D Generation with Spatially Scalable Generative Modeling
  20. DGHMesh: A Large-scale Dual-radar mmWave Dataset and Generalization-focused Benchmark for Human Mesh Reconstruction
  21. Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis
  22. SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
  23. WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention
  24. On Solving the Multiple Variable Gapped Longest Common Subsequence Problem
  25. FASE : A Fairness-Aware Spatiotemporal Event Graph Framework for Predictive Policing
  26. NeuroAI and Beyond: Bridging Between Advances in Neuroscience and Artificial Intelligence
  27. Virtual boundary integral neural network for three-dimensional exterior acoustic problems
  28. Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokinetics
  29. Low Light Image Enhancement Challenge at NTIRE 2026
  30. Peerispect: Claim Verification in Scientific Peer Reviews
  31. ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
  32. Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy
  33. Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation
  34. PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents
  35. Self-Supervised Super-Resolution for Sentinel-5P Hyperspectral Images
  36. Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance
  37. On The Mathematics of the Natural Physics of Optimization
  38. Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
  39. Does Welsh media need a review? Detecting bias in Nation.Cymru's political reporting
  40. Toward Reusability of AI Models Using Dynamic Updates of AI Documentation
  41. FlowC2S: Flowing from Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation
  42. STRIKE: Additive Feature-Group-Aware Stacking Framework for Credit Default Prediction
  43. Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection
  44. Characterizing Model-Native Skills
  45. STEP-PD: Stage-Aware and Explainable Parkinson's Disease Severity Classification Using Multimodal Clinical Assessments
  46. Polarization and Integration in Global AI Research
  47. Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
  48. AIRA: AI-Induced Risk Audit: A Structured Inspection Framework for AI-Generated Code
  49. How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function
  50. Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
  51. PBSBench: A Multi-Level Vision-Language Framework and Benchmark for Hematopathology Whole Slide Image Interpretation
  52. MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring
  53. Diverse Dictionary Learning
  54. Multi-Camera Self-Calibration in Sports Motion Capture: Leveraging Human and Stick Poses
  55. UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
  56. Causal-Temporal Event Graphs: A Formal Model for Recursive Agent Execution Traces
  57. Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells
  58. PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs
  59. Dual Strategies for Test-Time Adaptation
  60. Real-Time Cellist Postural Evaluation With On-Device Computer Vision
  61. VIDS: A Verified Imaging Dataset Standard for Medical AI
  62. From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
  63. ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization
  64. Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
  65. Learning Unanimously Acceptable Lotteries via Queries
  66. Edit Fidelity Field: Semantics-Aware Region Isolation for Training-Free Scene Text Editing
  67. Generative AI Technologies, Techniques & Tensions: A Primer
  68. A Probabilistic Consensus-Driven Approach for Robust Counterfactual Explanations
  69. Matlas: A Semantic Search Engine for Mathematics
  70. Trustworthy deep domain adaptation for wearable photoplethysmography signal analysis with decision-theoretic uncertainty quantification
  71. Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection
  72. Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading
  73. Dual-Anchoring: Addressing State Drift in Vision-Language Navigation
  74. UniMesh: Unifying 3D Mesh Understanding and Generation
  75. Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
  76. Language models recognize dropout and Gaussian noise applied to their activations
  77. Beyond the Bellman Fixed Point: Geometry and Fast Policy Identification in Value Iteration
  78. From Adaptation to Generalization: Adaptive Visual Prompting for Medical Image Segmentation
  79. HSG: Hyperbolic Scene Graph
  80. Learned Nonlocal Feature Matching and Filtering for RAW Image Denoising
  81. SegTTA: Training-Free Test-Time Augmentation for Zero-Shot Medical Imaging Segmentation
  82. HyKey: Hyperspectral Keypoint Detection and Matching in Minimally Invasive Surgery
  83. Attention Is not Everything: Efficient Alternatives for Vision
  84. DEM Refinement and Validation on the Lunar Surface Using Shape-from-Shading with Chandrayaan-2 OHRC Imagery
  85. MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
  86. Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation
  87. Neural Adjoint Method for Meta-optics: Accelerating Volumetric Inverse Design via Fourier Neural Operators
  88. A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon
  89. TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Laundering
  90. Project resilience as network robustness
  91. The Open-Weight Paradox: Why Restricting Access to AI Models May Undermine the Safety It Seeks to Protect
  92. DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs
  93. Algorithmic Contiguity from Low-Degree Heuristic II: Predicting Detection-Recovery Gaps
  94. On the Generalization Bounds of Symbolic Regression with Genetic Programming
  95. Contrastive Analysis of Linguistic Representations in Large Language Model Outputs through Structured Synthetic Data Generation and Abstracted N-gram Associations
  96. Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains
  97. RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification
  98. MESA: A Training-Free Multi-Exemplar Deep Framework for Restoring Ancient Inscription Textures
  99. Deep learning based Non-Rigid Volume-to-Surface Registration for Brain Shift compensation Using Point Cloud
  100. Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection
  101. StrEBM: A Structured Latent Energy-Based Model for Blind Source Separation
  102. Study and Improvement of Search Algorithms in Multi-Player Perfect-Information Games
  103. AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models
  104. Towards Generalizable Deepfake Image Detection with Vision Transformers
  105. Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer
  106. ArgBench: Benchmarking LLMs on Computational Argumentation Tasks
  107. LLM-Guided Strategy Synthesis for Scalable Equality Saturation
  108. Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations
  109. Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions
  110. SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization
  111. SPaRSe-TIME: Saliency-Projected Low-Rank Temporal Modeling for Efficient and Interpretable Time Series Prediction
  112. Formal Foundations of Agentic Business Process Management
  113. Logical Computational Linguistics
  114. FLARE: Task-agnostic embedding model evaluation through a normalization process
  115. Dual-Resolution Attention-Gated Deep Learning with Ordinal Regression for Diabetic Retinopathy Grading: A Quantified Assessment of Cross-Domain Generalization
  116. Neuro-Symbolic Resolution of Recommendation Conflicts in Multimorbidity Clinical Guidelines
  117. Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
  118. Capacity-Controlled Global Attention for Graph Transformers
  119. A Universal Avoidance Method for Diverse Multi-branch Generation
  120. R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection
  121. E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition
  122. Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
  123. SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
  124. Generalizable Face Forgery Detection via Separable Prompt Learning
  125. The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
  126. Chaos-Enhanced Prototypical Networks for Few-Shot Medical Image Classification
  127. Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video
  128. Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
  129. REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations
  130. Spectral Forensics of Diffusion Attention Graphs for Copy-Move Forgery Detection
  131. Depth Adaptive Efficient Visual Autoregressive Modeling
  132. HorizonBench: Long-Horizon Personalization with Evolving Preferences
  133. PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction
  134. Fully Analog Resonant Recurrent Neural Network via Metacircuit
  135. The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward
  136. HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification
  137. Understanding U.S. Users' Security and Privacy Transparency Needs for Consumer-Facing Generative AI
  138. Fractal Characterization of Low-Correlation Signals in AI-Generated Image Detection
  139. Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys
  140. Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation
  141. HORIZON: A Benchmark for In-the-wild User Behaviour Modeling
  142. REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning
  143. A Unified Compliance Aggregator Framework for Automated Multi-Tool Security Assessment of Linux Systems
  144. VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
  145. DORA Explorer: Improving the Exploration Ability of LLMs Without Training
  146. Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
  147. Fringe Projection Based Vision Pipeline for Autonomous Hard Drive Disassembly
  148. Yanasse: Finding New Proofs from Deep Vision's Analogies, Part 1
  149. Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study
  150. Region-Affinity Attention for Whole-Slide Breast Cancer Classification in Deep Ultraviolet Imaging
  151. PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory
  152. Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition
  153. Symplectic Inductive Bias for Data-Driven Target Reachability in Hamiltonian Systems
  154. EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents
  155. DREAM: Dynamic Retinal Enhancement with Adaptive Multi-modal Fusion for Expert Precision Medical Report Generation
  156. CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography
  157. SciDraw-6K: A Multilingual Scientific Illustration Dataset Generated by Google Gemini
  158. Calibrating Model-Based Evaluation Metrics for Summarization
  159. Learning to Control Summaries with Score Ranking
  160. Forecast Sports Outcomes under Efficient Market Hypothesis: Theoretical and Experimental Analysis of Odds-Only and Generalised Linear Models
  161. LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation
  162. Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization
  163. SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
  164. A Model and Estimation of the Bitcoin Transaction Fee
  165. Decentralised Trust and Security Mechanisms for IoT Networks at the Edge: A Comprehensive Review
  166. Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation
  167. Decomposing the Depth Profile of Fine-Tuning
  168. Intent-aligned Autonomous Spacecraft Guidance via Reasoning Models
  169. RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
  170. Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding
  171. UCCL-Zip: Lossless Compression Supercharged GPU Communication