mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 20 Apr 2026

525 papers

  1. AI-Native Network Controller: A Modular Framework for Safe Agentic Control of Multi-Domain Network InfrastructureLLM agents and tool use → Agentic AI for wireless networks
  2. Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMsMultimodal LLMs / vision-language models → Image editing and quality assessment
  3. Retrieval Augmented Generation Framework for the Nepali Legal Domain Question AnsweringRetrieval-augmented generation → Legal and financial RAG
  4. Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student ReasoningLLM reasoning → Mathematical reasoning
  5. Leveraging Vision-Language Models to Detect Attention in Educational VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs
  6. Reducing Credit Assignment Variance via Counterfactual Reasoning PathsLLM reasoning → Reinforcement learning for reasoning
  7. SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained DispatchLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Putting HUMANS first: Efficient LAM Evaluation with Human Preference AlignmentLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  9. JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language AgentsLLM agents and tool use → Tool learning and function calling
  10. From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems TestingEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  11. LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  12. Harmful Intent as a Geometrically Recoverable Feature of LLM Residual StreamsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  13. Less Is More: Cognitive Load and the Single-Prompt Ceiling in LLM Mathematical ReasoningLLM reasoning → Mathematical reasoning
  14. Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer CorrectnessLLM reasoning → Multimodal reasoning
  15. How Adversarial Environments Mislead Agentic AI?LLM agents and tool use → Agent threats, guardrails and governance
  16. From Natural Language to Executable Narsese: A Neuro-Symbolic Benchmark and Pipeline for Reasoning with NARSLLM reasoning → Reasoning benchmarks and evaluation
  17. Hierarchically Robust Zero-shot Vision-language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  18. ConvVitMamba: Efficient Multiscale Convolution, Transformer, and Mamba-Based Sequence modelling for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  19. Human-Guided Harm Recovery for Computer Use AgentsLLM agents and tool use → Agent threats, guardrails and governance
  20. Multi-Domain Learning with Global Expert MappingMixture-of-experts → Vision mixture-of-experts
  21. DUALVISION: RGB-Infrared Multimodal Large Language Models for Robust Visual ReasoningLLM reasoning → Multimodal reasoning +1
  22. AI scientists produce results without reasoning scientificallyLLM reasoning → Knowledge- and tool-augmented reasoning
  23. Geometric Decoupling: Diagnosing the Structural Instability of LatentDiffusion models → Diffusion foundations and sampling
  24. LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  25. HELM: Harness-Enhanced Long-horizon Memory for Vision-Language-Action ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  26. ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward SystemLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  27. Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUsMixture-of-experts → Efficient MoE training and inference systems
  28. Mango: Multi-Agent Web Navigation via Global-View OptimizationLLM agents and tool use → Web, search, and research agents
  29. An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language ModelsLLM safety and security → Jailbreaking
  30. Towards Understanding the Robustness of Sparse AutoencodersLLM safety and security → Jailbreaking +1
  31. Discrete Tilt MatchingDiffusion models → Discrete and text diffusion
  32. Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  33. A Controlled Benchmark of Visual State-Space Backbones with Domain-Shift and Boundary Analysis for Remote-Sensing SegmentationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  34. Towards Optimal Agentic Architectures for Offensive Security TasksLLM agents and tool use → Agent threats, guardrails and governance
  35. Characterizing AlphaEarth Embedding Geometry for Agentic Environmental ReasoningLLM agents and tool use → Multimodal and embodied agents
  36. Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model TrainingWorld models → Latent dynamics models and model-based RL +1
  37. Beyond Indistinguishability: Measuring Extraction Risk in LLM APIsLLM safety and security → Membership inference attacks
  38. Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
  39. Owner-Harm: A Missing Threat Model for AI Agent SafetyLLM agents and tool use → Agent threats, guardrails and governance
  40. From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic ComputersLLM agents and tool use → Agent threats, guardrails and governance
  41. Position: No Retroactive Cure for Infringement during TrainingLLM safety and security → Machine unlearning
  42. MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and RetrievalLLM reasoning → Mathematical reasoning +1
  43. Sessa: Selective State Space AttentionState-space sequence models (S4, Mamba) → Core SSM architectures for language
  44. Bounded Ratio Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  45. Agentic Forecasting using Sequential Bayesian Updating of Linguistic BeliefsLLM agents and tool use → Financial trading and forecasting agents
  46. When Can LLMs Learn to Reason with Weak Supervision?LLM reasoning → Reinforcement learning for reasoning
  47. Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache SteeringLLM reasoning → Test-time compute and efficient thinking +1
  48. MultiWorld: Scalable Multi-Agent Multi-View Video World ModelsWorld models → Video-generation world models and simulators
  49. MetaCloak-JPEG: JPEG-Robust Adversarial Perturbation for Preventing Unauthorized DreamBooth-Based Deepfake GenerationDiffusion models → Robustness, privacy and adversarial aspects +1
  50. OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  51. HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid ComputingEfficient LLM inference and serving → KV cache optimization
  52. LLM Safety From Within: Detecting Harmful Content with Internal RepresentationsLLM safety and security → Safety alignment, refusal and guardrails
  53. UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion ModelsLLM reasoning → Reinforcement learning for reasoning +1
  54. S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  55. Behind Harmful Compliance: Behavioral and Mechanistic Divergence Across LLM JailbreaksLLM safety and security → Safety alignment, refusal and guardrails
  56. MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  57. QRAFTI: An Agentic Framework for Empirical Research in Quantitative FinanceLLM agents and tool use → Financial trading and forecasting agents
  58. Too Correct to Learn: Reinforcement Learning on Saturated Reasoning DataLLM reasoning → Reinforcement learning for reasoning
  59. Aligning Language Models for Lyric-to-Melody Generation with Rule-Based Musical ConstraintsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  60. Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model SafetyLLM safety and security → Safety alignment, refusal and guardrails
  61. Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language ExplanationWorld models → World models for autonomous driving +1
  62. XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied EnvironmentsVision-language-action models → 3D and spatial-aware VLA
  63. WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time ReconciliationLLM agents and tool use → Agent memory systems
  64. Train Separately, Merge Together: Modular Post-Training with Mixture-of-ExpertsMixture-of-experts → MoE large language models
  65. NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order OptimizationDiffusion models → Discrete and text diffusion +1
  66. Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for SimulationEnd-to-end autonomous driving → Generative simulation for driving
  67. Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step SamplingLLM reasoning → Test-time compute and efficient thinking
  68. ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource SettingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  69. ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray ClassificationMultimodal LLMs / vision-language models → Medical vision-language models
  70. Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  71. CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent CapabilitiesLLM agents and tool use → Reinforcement learning for LLM agents
  72. River-LLM: Large Language Model Seamless Exit Based on KV ShareEfficient LLM inference and serving → Early exit and edge inference
  73. OpenGame: Open Agentic Coding for GamesLLM agents and tool use → Software engineering coding agents
  74. One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly DetectionDiffusion models → Flow matching, time series and science
  75. Randomly Initialized Networks Can Learn from Peer-to-Peer ConsensusKnowledge distillation → General knowledge distillation methods
  76. Training and Agentic Inference Strategies for LLM-based Manim Animation GenerationLLM reasoning → Multimodal reasoning +1
  77. ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  78. Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  79. ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented CompanionshipLLM agents and tool use → Social simulation and multi-agent debate
  80. HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational AgentsLLM agents and tool use → Agent memory systems
  81. AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video GenerationDiffusion models → Video generation
  82. Multilingual Training and Evaluation Resources for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  83. One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set PredictionDiffusion models → Discrete and text diffusion
  84. Reliability of AI Bots Footprints in GitHub Actions CI/CD WorkflowsLLM agents and tool use → Software engineering coding agents
  85. PARM: Pipeline-Adapted Reward ModelLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  86. EVE: Verifiable Self-Evolution of MLLMs via Executable Visual TransformationsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  87. Reasoning Models Know What's Important, and Encode It in Their ActivationsLLM reasoning → Reasoning benchmarks and evaluation
  88. CAARL: In-Context Learning for Interpretable Co-Evolving Time Series ForecastingLLM reasoning → Time series reasoning
  89. Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent IntelligenceLLM agents and tool use → General LLM agent frameworks and benchmarks
  90. EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  91. Geometry-Guided 3D Visual Token Pruning for Video-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  92. Domain-Specialized Object Detection via Model-Level Mixtures of ExpertsMixture-of-experts → Vision mixture-of-experts
  93. Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection DetectionLLM safety and security → Prompt injection and agent security
  94. AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  95. Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the WinnerLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  96. Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search AgentsLLM reasoning → Reinforcement learning for reasoning
  97. Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation StrategiesLLM reasoning → Knowledge- and tool-augmented reasoning +1
  98. Aether: Network Validation Using Agentic AI and Digital TwinLLM agents and tool use → Agentic AI for wireless networks
  99. AgenTEE: Confidential LLM Agent Execution on Edge DevicesLLM agents and tool use → Agent threats, guardrails and governance
  100. Towards an Agentic LLM-based Approach to Requirement Formalization from Unstructured SpecificationsLLM agents and tool use → Software engineering coding agents
All 525
  1. WebCompass: Towards Multimodal Web Coding Evaluation for Code Language ModelsLLM agents and tool use → Software engineering coding agents
  2. Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio InputsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  3. DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing ImageryDiffusion models → Inverse problems and image restoration
  4. Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language ModelsLLM reasoning → Audio-language model reasoning
  5. Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMsMechanistic interpretability → Steering and probing for LLM safety
  6. QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  7. Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM EditingEfficient LLM inference and serving → Speculative decoding
  8. MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-JudgeMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  9. Does "Do Differentiable Simulators Give Better Policy Gradients?'' Give Better Policy Gradients?Deep reinforcement learning methods → RL theory and sample complexity
  10. Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?Multimodal LLMs / vision-language models → Medical vision-language models
  11. Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled FuturesLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge ExplorationLLM agents and tool use → General LLM agent frameworks and benchmarks
  13. LoRaQ: Optimized Low Rank Approximation for 4-bit QuantizationDiffusion models → Diffusion foundations and sampling
  14. Retrieval-Augmented Multimodal Model for Fake News DetectionRetrieval-augmented generation → Multimodal RAG
  15. Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  16. Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context PrefillingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  17. Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural ContextsMultimodal LLMs / vision-language models → Image editing and quality assessment
  18. Class-specific diffusion models improve military object detection in a low-data domainDiffusion models → Image generation, text-to-image and editing
  19. Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix WeightingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  20. Architectural Design Decisions in AI Agent HarnessesLLM agents and tool use → General LLM agent frameworks and benchmarks
  21. Towards Human Motion World Models via Executable Behaviour RepresentationsWorld models → Embodied and robot world models
  22. Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data ScarcityWorld models → Medical and surgical world models
  23. The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style DataLLM reasoning → Reasoning benchmarks and evaluation
  24. JudgeMeNot: Personalizing Large Language Models to Emulate Judicial Reasoning in HebrewLLM reasoning → Reasoning for agents, planning and code
  25. First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic WorkflowsLLM agents and tool use → Medical and scientific domain agents
  26. SignDPO: Multi-level Direct Preference Optimisation for Skeleton-based Gloss-free Sign Language TranslationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  27. CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel CorporaSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  28. RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary EnvironmentsRetrieval-augmented generation → Agentic RAG, agents and memory
  29. Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea GenerationLLM agents and tool use → General LLM agent frameworks and benchmarks
  30. Neural Garbage Collection: Learning to Forget while Learning to ReasonLLM reasoning → Test-time compute and efficient thinking +1
  31. Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  32. AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain CurriculumLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. Mitigating Multimodal Hallucination via Phase-wise Self-rewardMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +2
  34. Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level RewardsLLM reasoning → Reinforcement learning for reasoning +1
  35. CADMAS-CTX: Contextual Capability Calibration for Multi-Agent DelegationLLM agents and tool use → Agent skill learning and evolution
  36. RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary ProgramsRetrieval-augmented generation → Privacy and security of RAG
  37. From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  38. ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace AnalysisLLM reasoning → Prompting and chain-of-thought reasoning
  39. LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research AgentLLM agents and tool use → Web, search, and research agents
  40. HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics AlignmentLLM reasoning → Reinforcement learning for reasoning
  41. Fisher Decorator: Refining Flow Policy via a Local Transport MapDiffusion models → Diffusion and flow policies for robotics +2
  42. OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  43. Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-ThoughtLLM reasoning → Reinforcement learning for reasoning
  44. Physics-Informed Causal MDPs for Sequential Constraint Repair in Engineering Simulation PipelinesDeep reinforcement learning methods → RL theory and sample complexity
  45. LoReC: Rethinking Large Language Models for Graph Data AnalysisLLM reasoning → Knowledge- and tool-augmented reasoning
  46. Can Explicit Physical Feasibility Benefit VLA Learning? An Empirical StudyVision-language-action models → Reinforcement learning and post-training +1
  47. LEPO: Latent Reasoning Policy Optimization for Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  48. AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual ReasoningLLM reasoning → Multimodal reasoning +2
  49. Latent Preference Modeling for Multi-Session Personalized Tool CallingLLM agents and tool use → Agent memory systems
  50. SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking
  51. ST-π: Structured SpatioTemporal VLA for Robotic ManipulationVision-language-action models → 3D and spatial-aware VLA
  52. OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic ManipulationDiffusion models → Diffusion and flow policies for robotics
  53. Design and Evaluation of a Culturally Adapted Multimodal Virtual Agent for PTSD ScreeningLLM agents and tool use → Medical and scientific domain agents
  54. GraSP: Graph-Structured Skill Compositions for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  55. Latent Abstraction for Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
  56. TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEsLLM agents and tool use → Agent threats, guardrails and governance
  57. On the Reliability of Computer Use AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  58. Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via LandingDiffusion models → Diffusion foundations and sampling
  59. Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEsMixture-of-experts → Expert routing strategies
  60. WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web AgentLLM reasoning → Reasoning for agents, planning and code +1
  61. PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State TrackingLLM reasoning → Reasoning benchmarks and evaluation
  62. Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. ScreenshotsLLM agents and tool use → GUI and mobile agents
  63. Re2MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware RefinementLLM reasoning → Spatial and embodied reasoning
  64. ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-TuningLLM reasoning → Spatial and embodied reasoning +1
  65. Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  66. DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 QuantizationEfficient LLM inference and serving → KV cache quantization
  67. AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action ModelsVision-language-action models → Tactile, force-aware and humanoid VLA
  68. Forget What Matters, Keep the Rest: Selective Unlearning of Informative TokensLLM safety and security → Machine unlearning
  69. Prompt Optimization Enables Stable Algorithmic Collusion in LLM AgentsLLM agents and tool use → Financial trading and forecasting agents
  70. Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIFLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  71. When Vision-Language Models Judge Without Seeing: Exposing Informativeness BiasMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  72. Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic BenchmarksMechanistic interpretability → Knowledge and representations inside LLMs
  73. Efficient Federated RLHF via Zeroth-Order Policy OptimizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  74. HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and ExecutionLLM agents and tool use → Software engineering coding agents
  75. Input-Side Variance Suppression under Non-Normal Transient Amplification in Continuous-Control Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  76. Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language ModelLLM agents and tool use → Reinforcement learning for LLM agents
  77. Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  78. Co-evolving Agent Architectures and Interpretable Reasoning for Automated OptimizationLLM reasoning → Reasoning for agents, planning and code +1
  79. OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RLVision-language-action models → Reinforcement learning and post-training +1
  80. WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM InferenceEfficient LLM inference and serving → Speculative decoding
  81. SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM AgentsLLM agents and tool use → Software engineering coding agents
  82. Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-PlayLLM reasoning → Reasoning for agents, planning and code +1
  83. MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache CompressionMixture-of-experts → MoE large language models +1
  84. SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  85. Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG SystemsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  86. Grokking of Diffusion Models: Case Study on Modular AdditionDiffusion models → Diffusion foundations and sampling
  87. Towards a New Grammar of Reasoning for Artificial Legal Intelligence and the Mecelle as Its Semantic Protocol
  88. Topological Void Analysis A Mathematical Framework for Systematic Technical Innovation Discovery in Knowledge Spaces
  89. Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps
  90. Poster: EdgeCitadel -- Hybrid NATS-MQTT Orchestration for Edge Multi-Agent Systems
  91. MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation
  92. PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference
  93. CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks
  94. BEACON: Behavioral Entropy Aggregation for Cross-Model Hallucination Detection in Large Language Models
  95. Post-training is (Massive) Supervised Learning
  96. GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendation
  97. Implicit Causal Graph Construction in Text via Chain Discovery
  98. ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
  99. Informing AI Policy Assessment using Large-Scale Simulation of Interventions
  100. Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms
  101. Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approach
  102. Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting
  103. Deep Learning for Multi-Antenna Modulation Recognition of Radio Signals
  104. OAMVOS:2nd Report for 5th PVUW MOSE Track
  105. AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method
  106. ParkingScenes: A Structured Dataset for End-to-End Autonomous Parking in Simulation Scenes
  107. WebSerial Vision Training for Microcontrollers: A Browser-Based Companion to On-Device CNN Training
  108. Discriminative-Generative Synergy for Occlusion Robust 3D Human Mesh Recovery
  109. Ternary Memristive Logic: Hardware for Reasoning Realized via Domain Algebra
  110. Option Pricing on Noisy Intermediate-Scale Quantum Computers: A Quantum Neural Network Approach
  111. TactileEval: A Step Towards Automated Fine-Grained Evaluation and Editing of Tactile Graphics
  112. More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems
  113. Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation
  114. SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution
  115. Rabies diagnosis in low-data settings: A comparative study on the impact of data augmentation and transfer learning
  116. Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features
  117. Proposing Topic Models and Evaluation Frameworks for Analyzing Associations with External Outcomes: An Application to Leadership Analysis Using Large-Scale Corporate Review Data
  118. Benchmarking PNW Model for MedMNIST to 100% Accuracy
  119. MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
  120. Collaborative Contextual Bayesian Optimization
  121. Gradient-Based Program Synthesis with Neurally Interpreted Languages
  122. Regulating Artificial Intimacy: From Locks and Blocks to Relational Accountability
  123. AC-SINDy: Compositional Sparse Identification of Nonlinear Dynamics
  124. Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph
  125. Formally Verified Patent Analysis via Dependent Type Theory: Machine-Checkable Certificates from a Hybrid AI + Lean 4 Pipeline
  126. A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders
  127. Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
  128. LegalBench-BR: A Benchmark for Evaluating Large Language Models on Brazilian Legal Decision Classification
  129. Subgraph Concept Networks: Concept Levels in Graph Classification
  130. HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images
  131. ParamBoost: Gradient Boosted Piecewise Cubic Polynomials
  132. Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning
  133. Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
  134. Task Switching Without Forgetting via Proximal Decoupling
  135. DDF2Pol: A Dual-Domain Feature Fusion Network for PolSAR Image Classification
  136. The Triadic Loop: A Framework for Negotiating Alignment in AI Co-hosted Livestreaming
  137. Trainability Beyond Linearity in Variational Quantum Objectives
  138. One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
  139. Quantum inspired qubit qutrit neural networks for real time financial forecasting
  140. Benchmarking Quantum Kernel Support Vector Machines Against Classical Baselines on Tabular Data: A Rigorous Empirical Study with Hardware Validation
  141. Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
  142. Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model
  143. The High Explosives and Affected Targets (HEAT) Dataset
  144. OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens
  145. Sparse Network Inference under Imperfect Detection and its Application to Ecological Networks
  146. Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning
  147. Rethinking Dataset Distillation: Hard Truths about Soft Labels
  148. A PPA-Driven 3D-IC Partitioning Selection Framework with Surrogate Models
  149. Preserving Clusters in Error-Bounded Lossy Compression of Scientific Particle Data
  150. Optimal Exploration of New Products under Assortment Decisions
  151. CrossPan: A Comprehensive Benchmark for Cross-Sequence Pancreas MRI Segmentation and Generalization
  152. EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion
  153. Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models
  154. CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans
  155. Streaming Structured Inference with Flash-SemiCRF
  156. Multi-Level Temporal Graph Networks with Local-Global Fusion for Industrial Fault Diagnosis
  157. Model-Agnostic Meta Learning for Class Imbalance Adaptation
  158. Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation
  159. REVEAL: Multimodal Vision-Language Alignment of Retinal Morphometry and Clinical Risks for Incident AD and Dementia Prediction
  160. Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling
  161. Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models
  162. URoPE: Universal Relative Position Embedding across Geometric Spaces
  163. DeltaSeg: Tiered Attention and Deep Delta Learning for Multi-Class Structural Defect Segmentation
  164. Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras
  165. Autonomous Skeletal Landmark Localization towards Agentic C-Arm Control
  166. Investigating Counterfactual Unfairness in LLMs towards Identities through Humor
  167. The Cost of Relaxation: Evaluating the Error in Convex Neural Network Verification
  168. Skillful Global Ocean Emulation and the Role of Correlation-Aware Loss
  169. Colour Extraction Pipeline for Odonates using Computer Vision
  170. Beyond One Output: Visualizing and Comparing Distributions of Language Model Generations
  171. Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP
  172. TrEEStealer: Stealing Decision Trees via Enclave Side Channels
  173. Align then Refine: Text-Guided 3D Prostate Lesion Segmentation
  174. Probing for Reading Times
  175. Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
  176. Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
  177. DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax
  178. MUA: Mobile Ultra-detailed Animatable Avatars
  179. ReCap: Lightweight Referential Grounding for Coherent Story Visualization
  180. T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability
  181. Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
  182. A multimodal and temporal foundation model for virtual patient representations at healthcare system scale
  183. Revisiting Active Sequential Prediction-Powered Mean Estimation
  184. Benchmarking System Dynamics AI Assistants: Cloud Versus Local LLMs on CLD Extraction and Discussion
  185. Dual Alignment Between Language Model Layers and Human Sentence Processing
  186. AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
  187. ConforNets: Latents-Based Conformational Control in OpenFold3
  188. SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy
  189. GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
  190. A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work
  191. Advancing Vision Transformer with Enhanced Spatial Priors
  192. Physics-Informed Neural Networks for Biological 2D+t Reaction-Diffusion Systems
  193. FUSE: Ensembling Verifiers with Zero Labeled Data
  194. Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk
  195. ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
  196. Duality for the Adversarial Total Variation
  197. Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
  198. Symbolic Synthesis for LTLf+ Obligations
  199. IDOBE: Infectious Disease Outbreak forecasting Benchmark Ecosystem
  200. Document-as-Image Representations Fall Short for Scientific Retrieval
  201. Learning the Riccati solution operator for time-varying LQR via Deep Operator Networks
  202. Bayesian experimental design: grouped geometric pooled posterior via ensemble Kalman methods
  203. Barrier-enforced multi-objective optimization for direct point and sharp interval forecasting
  204. Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD
  205. LQM: Linguistically Motivated Multidimensional Quality Metrics for Machine Translation
  206. Safe Control using Learned Safety Filters and Adaptive Conformal Inference
  207. Physics-Informed Neural Networks: A Didactic Derivation of the Complete Training Cycle
  208. Multi-Scale Reversible Chaos Game Representation: A Unified Framework for Sequence Classification
  209. SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
  210. A Generalized Synthetic Control Method for Baseline Estimation in Demand Response Services
  211. Partner-aware Peptide-Protein Interaction Prediction and Target-conditioned Peptide Generation
  212. Using large language models for embodied planning introduces systematic safety risks
  213. Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective
  214. Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
  215. Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
  216. AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning
  217. Conformal Robust Set Estimation
  218. Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems
  219. Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Models
  220. BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources
  221. Spectral bandits for smooth graph functions
  222. MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline
  223. Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms
  224. Six Llamas: Comparative Religious Ethics Through LoRA-Adapted Language Models
  225. Adaptive Kernel Selection for Kernelized Diffusion Maps
  226. Bridge-Centered Metapath Classification Using R-GCN-VGAE for Disaster-Resilient Maintenance Decisions
  227. AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment
  228. Understanding the Prompt Sensitivity
  229. Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
  230. The implicated scientist: on the role of AI researchers in the development of weapons systems
  231. Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning
  232. Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation
  233. IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters
  234. Dissecting AI Trading: Behavioral Finance and Market Bubbles
  235. Label-Efficient Bilateral Attention for Parkinson's Disease Screening from Wrist-Worn IMU Signals
  236. DSA-CycleGAN: A Domain Shift Aware CycleGAN for Robust Multi-Stain Glomeruli Segmentation
  237. EAST: Early Action Prediction Sampling Strategy with Token Masking
  238. LBFTI: Layer-Based Facial Template Inversion for Identity-Preserving Fine-Grained Face Reconstruction
  239. PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues
  240. Tight Auditing of Differential Privacy in MST and AIM
  241. Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems
  242. Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation
  243. FregeLogic at SemEval 2026 Task 11: A Hybrid Neuro-Symbolic Architecture for Content-Robust Syllogistic Validity Prediction
  244. OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
  245. Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference
  246. Predictive Modelling of Natural Medicinal Compounds for Alzheimer disease Using Machine Learning and Cheminformatics
  247. Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection
  248. Scale-free adaptive planning for deterministic dynamics & discounted rewards
  249. On the Importance and Evaluation of Narrativity in Natural Language AI Explanations
  250. Symmetry Guarantees Statistic Recovery in Variational Inference
  251. Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support
  252. Exploring Concreteness Through a Figurative Lens
  253. An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal
  254. Relative State Estimation using Event-Based Propeller Sensing
  255. Spike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization
  256. Dissipative Latent Residual Physics-Informed Neural Networks for Modeling and Identification of Electromechanical Systems
  257. Block-encodings as programming abstractions: The Eclipse Qrisp BlockEncoding Interface
  258. LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation
  259. Incremental learning for audio classification with Hebbian Deep Neural Networks
  260. MARCO: Navigating the Unseen Space of Semantic Correspondence
  261. Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation
  262. Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
  263. DeepRitzSplit Neural Operator for Phase-Field Models via Energy Splitting
  264. Long-Text-to-Image Generation via Compositional Prompt Decomposition
  265. DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
  266. LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL
  267. Style-Based Neural Architectures for Real-Time Weather Classification
  268. Medical Image Understanding Improves Survival Prediction via Visual Instruction Tuning
  269. Where Do Self-Supervised Speech Models Become Unfair?
  270. Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols
  271. Horospherical Depth and Busemann Median on Hadamard Manifolds
  272. Semantic-based Distributed Learning for Diverse and Discriminative Representations
  273. FSEVAL: Feature Selection Evaluation Toolbox and Dashboard
  274. Model in Distress: Sentiment Analysis on French Synthetic Social Media
  275. Is SAM3 ready for pathology segmentation?
  276. Instruction-as-State: Environment-Guided and State-Conditioned Semantic Understanding for Embodied Navigation
  277. EEG-Based Emergency Braking Intensity Prediction Using Blind Source Separation
  278. Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
  279. TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics
  280. Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
  281. A Control Architecture for Training-Free Memory Use
  282. A Comparative Evaluation of Geometric Accuracy in NeRF and Gaussian Splatting
  283. Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages
  284. Centre manifold theorem for maps along manifolds of fixed points
  285. Linear-Time and Constant-Memory Text Embeddings Based on Recurrent Language Models
  286. Friction-Augmented Drifting Models for Resource-Efficient Domain Translation
  287. Scalable Neighborhood-Based Multi-Agent Actor-Critic
  288. Towards Multi-View Sign Language Understanding: A Benchmark Dataset and Baseline
  289. STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs
  290. Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translation
  291. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
  292. Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models
  293. FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs
  294. State Transfer Reveals Reuse in Controlled Routing
  295. mlr3torch: A Deep Learning Framework in R based on mlr3 and torch
  296. AI-based Waste Mapping for Addressing Climate-Exacerbated Flood Risk
  297. Attention-ResUNet for Automated Fetal Head Segmentation
  298. Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
  299. Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
  300. Distributional Off-Policy Evaluation with Deep Quantile Process Regression
  301. AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization
  302. Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
  303. An `Inverse' Experimental Framework to Estimate Market Efficiency
  304. Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition
  305. Chatting about Conditional Trajectory Prediction
  306. TLoRA: Task-aware Low Rank Adaptation of Large Language Models
  307. Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents
  308. FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
  309. Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion
  310. NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  311. The Collaboration Gap in Human-AI Work
  312. DSAINet: An Efficient Dual-Scale Attentive Interaction Network for General EEG Decoding
  313. Decision-Aware Attention Propagation for Vision Transformer Explainability
  314. Generalization Boundaries of Fine-Tuned Small Language Models for Graph Structural Inference
  315. Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles
  316. Autonomous Unmanned Aircraft Systems for Enhanced Search and Rescue of Drowning Swimmers: Image-Based Localization and Mission Simulation
  317. Mix and Match: Context Pairing for Scalable Topic-Controlled Educational Summarisation
  318. Predicting LLM Compression Degradation from Spectral Statistics
  319. Implicit neural representations as a coordinate-based framework for continuous environmental field reconstruction from sparse ecological observations
  320. Dynamic Risk Assessment by Bayesian Attack Graphs and Process Mining
  321. Modeling Human Perspectives with Socio-Demographic Representations
  322. Towards Real-Time ECG and EMG Modeling on μNPUs
  323. Enhancing Anomaly-Based Intrusion Detection Systems with Process Mining
  324. Towards a Foundation-Model Paradigm for Aerodynamic Prediction in Three-dimensional Design
  325. ExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G Networks
  326. INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval
  327. GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
  328. HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval
  329. Variational Autoencoder Domain Adaptation for Cross-System Generalization in ML-Based SOP Monitoring
  330. CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement
  331. How Creative Are Large Language Models in Generating Molecules?
  332. Clusterability-Based Assessment of Potentially Noisy Views for Multi-View Clustering
  333. Boltzmann Machine Learning with a Parallel, Persistent Markov chain Monte Carlo method for Estimating Evolutionary Fields and Couplings from a Protein Multiple Sequence Alignment
  334. Multi-View Hierarchical Graph Neural Network for Sketch-Based 3D Shape Retrieval
  335. Neural Shape Operator Surrogates -- Expression Rate Bounds
  336. SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression
  337. Trustworthy Endoscopic Super-Resolution
  338. Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection
  339. Employing General-Purpose and Biomedical Large Language Models with Advanced Prompt Engineering for Pharmacoepidemiologic Study Design
  340. Latent Fourier Transform
  341. Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization
  342. ltzGLUE: Luxembourgish General Language Understanding Evaluation
  343. Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations
  344. Identifying Ethical Biases in Action Recognition Models
  345. E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
  346. From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?
  347. A Sugeno Integral View of Binarized Neural Network Inference
  348. TPS-CalcBench: A Benchmark and Diagnostic Evaluation Framework for LLM Analytical Calculation Competence in Hypersonic Thermal Protection System Engineering
  349. MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
  350. DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection
  351. The Umwelt Representation Hypothesis: Rethinking Universality
  352. Chatting about Upper-Body Expressive Human Pose and Shape Estimation
  353. Federated Rule Ensemble Method in Medical Data
  354. Complex normalizing flows can almost be information K"ahler-Ricci flows
  355. ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection
  356. ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering
  357. A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
  358. How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers
  359. Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?
  360. Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding
  361. Prompting Foundation Models for Zero-Shot Ship Instance Segmentation in SAR Imagery
  362. Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors
  363. Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval
  364. MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition
  365. ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval
  366. Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions
  367. Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
  368. Exploring Boundary-Aware Spatial-Frequency Fusion for Camouflaged Object Detection
  369. Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models
  370. Sharpening Lightweight Models for Generalized Polyp Segmentation: A Boundary Guided Distillation from Foundation Models
  371. Periodic Steady-State Control of a Handkerchief-Spinning Task Using a Parallel Anti-Parallelogram Tendon-driven Wrist
  372. M100: An Orchestrated Dataflow Architecture Powering General AI Computing
  373. On the Emergence of Syntax by Means of Local Interaction
  374. PlankFormer: Robust Plankton Instance Segmentation via MAE-Pretrained Vision Transformers and Pseudo Community Image Generation
  375. UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement
  376. AI Approach for MRI-only Full-Spine Vertebral Segmentation and 3D Reconstruction in Paediatric Scoliosis
  377. Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research
  378. QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks
  379. PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty
  380. How Non-Linguistic Is the Indus Sign System? A Synthetic-Baseline Scorecard
  381. Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM
  382. A novel LSTM music generator based on the fractional time-frequency feature extraction
  383. GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning
  384. AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion
  385. Navigating the Conceptual Multiverse
  386. Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective
  387. Enabling AI ASICs for Zero Knowledge Proof
  388. Party Autonomy in Determining the Law Applicable to Non-contractual Obligations concerning Cross-Border Data Transfers
  389. Perturbation Sensitivity of Maximum-Likelihood Pairwise Ranking in Computational Decision Systems
  390. Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition
  391. Optimally Bridging Semantics and Data: Generative Semantic Communication via Schr"odinger Bridge
  392. View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity
  393. Weakly-Supervised Referring Video Object Segmentation through Text Supervision
  394. Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval
  395. TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications
  396. Structure-Adaptive Sparse Diffusion in Voxel Space for 3D Medical Image Enhancement
  397. SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
  398. LLM-AUG: Robust Wireless Data Augmentation with In-Context Learning in Large Language Models
  399. A Quasi-Experimental Developer Study of Security Training in LLM-Assisted Web Application Development
  400. Community-Led AI Integration for Wildfire Risk Assessment: A Participatory AI Literacy and Explainability Integration (PALEI) Framework in Los Angeles, CA
  401. Evolutionary Negative Module Pruning for Better LoRA Merging
  402. HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation
  403. Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
  404. Source-Free Domain Adaptation with Vision-Language Prior
  405. IncreFA: Breaking the Static Wall of Generative Model Attribution
  406. Score-Based Matching with Target Guidance for Cryo-EM Denoising
  407. MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
  408. Voronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolution
  409. RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models
  410. GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion
  411. FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching
  412. Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation
  413. Concurrent Criterion Validation of a Validity Screen for LLM Confidence Signals via Selective Prediction
  414. Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics
  415. Screen Before You Interpret: A Portable Validity Protocol for Benchmark-Based LLM Confidence Signals
  416. Modeling Higher-Order Brain Interactions via a Multi-View Information Bottleneck Framework for fMRI-based Psychiatric Diagnosis
  417. Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels
  418. DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
  419. Before You Interpret the Profile: Validity Scaling for LLM Metacognitive Self-Report
  420. The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
  421. Improving reproducibility by controlling random seed stability in machine learning based estimation via bagging
  422. COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams
  423. Path-Based Quantum Meta-Learning for Adaptive Optimization of Reconfigurable Intelligent Surfaces
  424. Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation
  425. Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts