mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 2 Dec 2025

366 papers

  1. Virtual Parameter Sharpening: Dynamic Low-Rank Perturbations for Inference-Time Reasoning EnhancementLLM reasoning → Test-time compute and efficient thinking
  2. Adaptive Multi-Agent Reasoning for Text-to-Video RetrievalLLM reasoning → Multimodal reasoning +2
  3. Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under CompressionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  4. Self-Improving VLM Judges Without Human AnnotationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  5. PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward ModelingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
  6. When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier ModelsLLM safety and security → Safety alignment, refusal and guardrails
  7. Measuring Agents in ProductionLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Unlocking hidden biomolecular conformational landscapes in diffusion models at inference timeDiffusion models → Flow matching, time series and science
  9. A Gossip-Enhanced Communication Substrate for Agentic AI: Toward Decentralized Coordination in Large-Scale Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  10. SpatialReasoner: Active Perception for Large-Scale 3D Scene UnderstandingLLM reasoning → Spatial and embodied reasoning +1
  11. Thucy: An LLM-based Multi-Agent System for Claim Verification across Relational DatabasesLLM agents and tool use → Web, search, and research agents
  12. Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge RetrievalMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  13. When Do Symbolic Solvers Enhance Reasoning in Large Language Models?LLM reasoning → Reasoning benchmarks and evaluation
  14. Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World TasksLLM agents and tool use → Agent threats, guardrails and governance
  15. PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space RefinementDiffusion models → Image generation, text-to-image and editing
  16. ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground TruthLLM reasoning → Reinforcement learning for reasoning +1
  17. Iterative Tilting for Diffusion Fine-TuningDiffusion models → Diffusion foundations and sampling
  18. Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  19. InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  20. AGENTSAFE: A Unified Framework for Ethical Assurance and Governance in Agentic AILLM agents and tool use → Agent threats, guardrails and governance
  21. Plantain: Plan-Answer Interleaved ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  22. Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR SpectraDiffusion models → Flow matching, time series and science
  23. Hierarchical Process Reward Models are Symbolic Vision LearnersLLM reasoning → Multimodal reasoning +1
  24. Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  25. E-valuator: Reliable Agent Verifiers with Sequential Hypothesis TestingLLM reasoning → Reasoning for agents, planning and code +1
  26. MagicQuillV2: Precise and Interactive Image Editing with Layered Visual CuesDiffusion models → Image generation, text-to-image and editing
  27. CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  28. Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional ModelingDiffusion models → Diffusion and flow policies for robotics
  29. OneThinker: All-in-one Reasoning Model for Image and VideoLLM reasoning → Multimodal reasoning +1
  30. MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and GenerationDiffusion models → Audio, speech and music
  31. SMP: Reusable Score-Matching Motion Priors for Physics-Based Character ControlOffline RL and imitation learning from data → Imitation learning methods
  32. FLAT: FLow-Aligned Training of Unrolled Networks for MRI ReconstructionDiffusion models → Medical imaging and segmentation
  33. Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-JudgeLLM reasoning → Reasoning benchmarks and evaluation
  34. DynamicVerse: A Physically-Aware Multimodal Framework for 4D World ModelingWorld models → Video-generation world models and simulators
  35. U4D: Uncertainty-Aware 4D World Modeling from LiDAR SequencesWorld models → World modeling from LiDAR generation
  36. InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent CollaborationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  37. Contextual Image Attack: How Visual Context Exposes Multimodal Safety VulnerabilitiesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  38. AutoNeural: Co-Designing Vision-Language Models for NPU InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  39. Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  40. MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  41. VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial ModelingVision-language-action models → VLA architectures and generalization
  42. Glance: Accelerating Diffusion Models with 1 SampleDiffusion models → Diffusion foundations and sampling
  43. MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training ParadigmMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  44. Fast-Decoding Diffusion Language Models via Progress-Aware Confidence SchedulesDiffusion models → Discrete and text diffusion +1
  45. Think in Parallel, Answer as One: Logit Averaging for Open-Ended ReasoningLLM reasoning → Test-time compute and efficient thinking
  46. Taming Camera-Controlled Video Generation with Verifiable Geometry RewardDiffusion models → Video generation +1
  47. EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  48. VLM as Strategist: Adaptive Generation of Safety-critical Testing Scenarios via Guided DiffusionDiffusion models → Diffusion and flow policies for robotics
  49. ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement LearningLLM reasoning → Multimodal reasoning
  50. Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling ApproachLLM reasoning → Spatial and embodied reasoning +2
  51. From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle VelocityDiffusion models → Flow matching, time series and science
  52. SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model AlignmentLLM reasoning → Reinforcement learning for reasoning +1
  53. TriLex: A Framework for Multilingual Sentiment Analysis in Low-Resource South African LanguagesRetrieval-augmented generation → Generation and context integration
  54. Diagnose, Correct, and Learn from Manipulation Failures via Visual SymbolsVision-language-action models → Failure recovery and robustness
  55. FiMMIA: scaling semantic perturbation-based membership inference across modalitiesLLM safety and security → Membership inference attacks
  56. Reinforcement learning for irreversible reinsurance problems: the randomized singular control approachDeep reinforcement learning methods → RL theory and sample complexity
  57. Diffusion-Prior Split Gibbs Sampling for Synthetic Aperture Radar Imaging under Incomplete MeasurementsDiffusion models → Inverse problems and image restoration
  58. Channel Knowledge Map Construction via Physics-Inspired Diffusion Model Without Prior ObservationsDiffusion models → Diffusion for compression and wireless
  59. Reasoning-Aware Multimodal Fusion for Hateful Video DetectionLLM reasoning → Reasoning benchmarks and evaluation
  60. DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in InteractionsState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
  61. Emergent Bayesian Behaviour and Optimal Cue Combination in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  62. GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual GroundingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  63. CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual TransferLLM safety and security → Safety alignment, refusal and guardrails
  64. VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning ParadigmMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  65. Learning What to Attend First: Modality-Importance-Guided Reasoning for Reliable Multimodal Emotion UnderstandingLLM reasoning → Audio-language model reasoning +1
  66. Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM InteractionsLLM agents and tool use → Agent threats, guardrails and governance
  67. PGP-DiffSR: Phase-Guided Progressive Pruning for Efficient Diffusion-based Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  68. Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete LatentsDiffusion models → Flow matching, time series and science
  69. Locality-Aware Continual Unlearning for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  70. Zero-Shot Instruction Following in RL via Structured LTL RepresentationsDeep reinforcement learning methods → Interpretable and logic-guided RL
  71. SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy OptimizationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  72. PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design UnderstandingLLM reasoning → Multimodal reasoning
  73. RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation IntelligenceLLM reasoning → Multimodal reasoning
  74. SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action PredictionOffline RL and imitation learning from data → Robot manipulation imitation learning
  75. Spoken Conversational Agents with Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  76. PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and EditingLLM agents and tool use → Web, search, and research agents
  77. Training Diffusion Policies via Prior-Mapping Co-EvolutionDiffusion models → Diffusion and flow policies for robotics +1
  78. From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning TasksLLM reasoning → Reinforcement learning for reasoning
  79. Co-speech Gesture Video Generation via Motion-Based Graph RetrievalDiffusion models → Audio, speech and music
  80. From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific LiteratureMultimodal LLMs / vision-language models → Medical vision-language models
  81. CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  82. Inference-Time Distillation: Cost-Efficient Agents Without Fine-Tuning or Manual Prompt EngineeringLLM agents and tool use → General LLM agent frameworks and benchmarks
  83. WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query TokensMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  84. Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaborationLLM agents and tool use → Agent threats, guardrails and governance
  85. Generative Multi-modal Feedback for Singing Voice Synthesis EvaluationLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  86. SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of ExpertsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  87. GeoDiT: A Diffusion-based Vision-Language Model for Geospatial UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  88. COPE: Chain-Of-Thought Prediction Engine for Open-Source Large Language Model Based Stroke Outcome Prediction from Clinical NotesLLM reasoning → Clinical and biomedical applications
  89. dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language ModelMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  90. YingVideo-MV: Music-Driven Multi-Stage Video GenerationDiffusion models → Audio, speech and music
  91. Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language UnderstandingLLM reasoning → Spatial and embodied reasoning
  92. Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics ShiftsOffline RL and imitation learning from data → Offline RL algorithms
  93. UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-MakingMultimodal LLMs / vision-language models → Medical vision-language models +1
  94. WorldPack: Dynamic Frame Compression for Long-context Video World ModelingWorld models → Video-generation world models and simulators
  95. Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and ExplorationLLM reasoning → Spatial and embodied reasoning
  96. See, Think, Learn: A Self-Taught Multimodal ReasonerLLM reasoning → Multimodal reasoning +1
  97. When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  98. Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing ResourcesMultimodal LLMs / vision-language models → Medical vision-language models +1
  99. Agentic AI for Clustering, Relationship Discovery, and Semantic Trading in Prediction MarketsLLM agents and tool use → Financial trading and forecasting agents
  100. Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data FilteringOffline RL and imitation learning from data → Offline RL algorithms
All 366
  1. WorldMM: Dynamic Multimodal Memory Agent for Long Video ReasoningLLM reasoning → Multimodal reasoning +1
  2. GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
  3. Generalizing Vision-Language Models with Dedicated Prompt GuidanceMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  4. The brain-AI convergence: Predictive and generative world models for general-purpose computationWorld models → World models for navigation
  5. Vehicle Dynamics Embedded World Models for Autonomous DrivingWorld models → World models for autonomous driving +1
  6. Decentralized Multi-Agent System with Trust-Aware CommunicationLLM agents and tool use → Agent threats, guardrails and governance
  7. Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical OraclesLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  8. WISE: Weighted Iterative Society-of-Experts for Robust Multimodal Multi-Agent DebateLLM agents and tool use → Social simulation and multi-agent debate
  9. Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearchLLM agents and tool use → Multimodal and embodied agents
  10. Process-Centric Analysis of Agentic Software SystemsLLM agents and tool use → Software engineering coding agents
  11. Risk-Sensitive Q-Learning in Continuous Time with Application to Dynamic Portfolio SelectionDeep reinforcement learning methods → RL theory and sample complexity
  12. Reinforcement Learning in POMDP's via Direct Gradient AscentDeep reinforcement learning methods → RL theory and sample complexity
  13. MoE-Enhanced Multi-Domain Feature Selection and Fusion for Fast Map-Free Trajectory PredictionMixture-of-experts → MoE in reinforcement learning and robotics
  14. VACoT: Rethinking Visual Data Augmentation with VLMsLLM reasoning → Multimodal reasoning +1
  15. Beyond Playtesting: A Generative Multi-Agent Simulation System for Massively Multiplayer Online GamesLLM agents and tool use → Reinforcement learning for LLM agents
  16. Understanding and Harnessing Sparsity in Unified Multimodal ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  17. FOVA: Offline Federated Reinforcement Learning with Mixed-Quality DataOffline RL and imitation learning from data → Offline RL algorithms
  18. Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science PerspectiveLLM reasoning → Spatial and embodied reasoning
  19. Video Diffusion Models Excel at Tracking Similar-Looking Objects Without SupervisionDiffusion models → Video generation
  20. SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial VerificationEfficient LLM inference and serving → Speculative decoding
  21. Retrieval-Augmented Memory for Online LearningRetrieval-augmented generation → Generation and context integration
  22. Towards autonomous normative multi-agent systems for Human-AI software engineering teamsLLM agents and tool use → Software engineering coding agents
  23. LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance +1
  24. COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA SolversMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. OmniGuard: Unified Omni-Modal Guardrails with Deliberate ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  26. Medication counseling with large language models: balancing flexibility and rigidity
  27. Investigating Anthropometric Fidelity in SAM 3D Body
  28. MedPI: Evaluating AI Systems in Medical Patient-facing Interactions
  29. Variance-Aware LLM Annotation for Strategy Research: Sources, Diagnostics, and a Protocol for Reliable Measurement
  30. Noise-Driven Persona Formation in Reflexive Neural Language Generation
  31. Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
  32. Assessing Greenspace Attractiveness with ChatGPT, Claude, and Gemini: Do AI Models Reflect Human Perceptions?
  33. Agent-Based Modular Learning for Multimodal Emotion Recognition in Human-Agent Systems
  34. TECM*: A Data-Driven Assessment to Reinforcement Learning Methods and Application to Heparin Treatment Strategy for Surgical Sepsis
  35. Enhancing Automatic Speech Recognition Through Integrated Noise Detection Architecture
  36. CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models
  37. Functional Random Forest with Adaptive Cost-Sensitive Splitting for Imbalanced Functional Data Classification
  38. Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization
  39. PrunedCaps: A Case For Primary Capsules Discrimination
  40. POrTAL: Plan-Orchestrated Tree Assembly for Lookahead
  41. Small Language Models Reshape Higher Education: Courses, Textbooks, and Teaching
  42. ASCIIBench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text
  43. Can machines perform a qualitative data analysis? Reading the debate with Alan Turing
  44. Towards Contextual Sensitive Data Detection
  45. Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
  46. Retrofitting Earth System Models with Cadence-Limited Neural Operator Updates
  47. Robust Tabular Foundation Models
  48. HydroDCM: Hydrological Domain-Conditioned Modulation for Cross-Reservoir Inflow Prediction
  49. Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction
  50. Associating Healthcare Teamwork with Patient Outcomes for Predictive Analysis
  51. Prior preferences in active inference agents: soft, hard, and goal shaping
  52. ASPEN: An Adaptive Spectral Physics-Enabled Network for Ginzburg-Landau Dynamics
  53. Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors
  54. BlendedNet++: A dataset and benchmark for field-resolved aerodynamics and inverse design of blended wing body aircraft
  55. PyroFocus: A Deep Learning Approach to Real-Time Wildfire Detection in Multispectral Remote Sensing Imagery
  56. Learning Network Sheaves for AI-native Semantic Communication
  57. 2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition
  58. Novelty detection on path space
  59. How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
  60. LLM-Guided Material Inference for 3D Point Clouds
  61. Object Counting with GPT-4o and GPT-5: A Comparative Study
  62. Convergence of a class of gradient-free optimisation schemes when the objective function is noisy, irregular, or both
  63. Perch 2.0 transfers 'whale' to underwater tasks
  64. Kaleidoscopic Scintillation Event Imaging
  65. Identifying attributions of causality in political text
  66. A Multi-Agent, Policy-Gradient approach to Network Routing
  67. Flux4D: Flow-based Unsupervised 4D Reconstruction
  68. Scaling Internal-State Policy-Gradient Methods for POMDPs
  69. Does Head Pose Correction Improve Biometric Facial Recognition?
  70. Ultra-Strong Gradient Diffusion MRI with Self-Supervised Learning for Prostate Cancer Characterization
  71. Enhancing Job Matching: Occupation, Skill and Qualification Linking with the ESCO and EQF taxonomies
  72. GRAND: Guidance, Rebalancing, and Assignment for Networked Dispatch in Multi-Agent Path Finding
  73. In Situ Quantum Analog Pulse Characterization via Structured Signal Processing
  74. Neighborhood density estimation using space-partitioning based hashing schemes
  75. Drainage: A Unifying Framework for Addressing Class Uncertainty
  76. Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping
  77. Multi-Agent Reinforcement Learning and Real-Time Decision-Making in Robotic Soccer for Virtual Environments
  78. Contrastive Deep Learning for Variant Detection in Wastewater Genomic Sequencing
  79. Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
  80. Assessing Extrapolation of Peaks Over Thresholds with Martingale Testing
  81. Real-Time Structural Health Monitoring with Bayesian Neural Networks: Distinguishing Aleatoric and Epistemic Uncertainty for Digital Twin Frameworks
  82. Temporal Graph Neural Networks for Early Anomaly Detection and Performance Prediction via PV System Monitoring Data
  83. A Discrete Neural Operator with Adaptive Sampling for Surrogate Modeling of Parametric Transient Darcy Flows in Porous Media
  84. Beyond Additivity: Sparse Isotonic Shapley Regression toward Nonlinear Explainability
  85. PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer
  86. The BEAT-CF Causal Model: A model for guiding the design of trials and observational analyses of cystic fibrosis exacerbations
  87. Detecting AI Hallucinations in Finance: An Information-Theoretic Method Cuts Hallucination Rate by 92%
  88. PPTArena: A Benchmark for PowerPoint Editing
  89. MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
  90. Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
  91. ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
  92. Learning Physically Consistent Lagrangian Control Models Without Acceleration Measurements
  93. The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Models
  94. LORE: A Large Generative Model for Search Relevance
  95. TokenPowerBench: Benchmarking the Power Consumption of LLM Inference
  96. AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry
  97. Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
  98. In-Context Sync-LoRA for Portrait Video Editing
  99. SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting
  100. From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars?
  101. DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
  102. Invasive Context Engineering to Control Large Language Models
  103. TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
  104. GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
  105. Fine-Tuned Large Language Models for Logical Translation: Reducing Hallucinations with Lang2Logic
  106. ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomics
  107. Rethinking Generalized BCIs: Benchmarking 340,000+ Unique Algorithmic Configurations for EEG Mental Command Decoding
  108. BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection
  109. Identification of Multivariate Measurement Error Models
  110. Flexible Gravitational-Wave Parameter Estimation with Transformers
  111. Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis
  112. Lumos: Let there be Language Model System Certification
  113. UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement
  114. Layout Anything: One Transformer for Universal Room Layout Estimation
  115. Representation of Inorganic Synthesis Reactions and Prediction: Graphical Framework and Datasets
  116. Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
  117. LoVoRA: Text-guided and Mask-free Video Object Removal and Addition with Learnable Object-aware Localization
  118. EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis
  119. DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation
  120. Fast Gaussian Process Approximations for Autocorrelated Data
  121. Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
  122. Hypothesis Testing for Generalized Thurstone Models
  123. In Silico Development of Psychometric Scales: Feasibility of Representative Population Data Simulation with LLMs
  124. Towards a fully differentiable digital twin for solar cells
  125. Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in ± 1, ± i
  126. Model-Based Diagnosis with Multiple Observations: A Unified Approach for C Software and Boolean Circuits
  127. Polar Perspectives: Evaluating 2-D LiDAR Projections for Robust Place Recognition with Visual Foundation Models
  128. OptPO: Optimal Rollout Allocation for Test-time Policy Optimization
  129. The future of AI in critical mineral exploration
  130. Assessing the performance of correlation-based multi-fidelity neural emulators
  131. MICCAI STSR 2025 Challenge: Semi-Supervised Teeth and Pulp Segmentation and CBCT-IOS Registration
  132. Spectral Joint Subspace Estimation for Heterogeneous Multi-View Data: Geometry and Reweighting
  133. Leveraging generative adversarial networks with spatially adaptive denormalization for multivariate stochastic seismic data inversion
  134. RFOP: Rethinking Fusion and Orthogonal Projection for Face-Voice Association
  135. Adaptive Decentralized Federated Learning for Robust Optimization
  136. Are Detectors Fair to Indian IP-AIGC? A Cross-Generator Study
  137. GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace
  138. Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?
  139. Bangla Hate Speech Classification with Fine-tuned Transformer Models
  140. Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages
  141. promptolution: A Unified, Modular Framework for Prompt Optimization
  142. A Comparative Study on How Data Normalization Affects Zero-Shot Generalization in Time Series Foundation Models
  143. Revisiting Theory of Contrastive Learning for Domain Generalization
  144. Defense That Attacks: How Robust Models Become Better Attackers
  145. Tempering the Bayes Filter towards Improved Model-Based Estimation
  146. BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion
  147. A benchmark dataset for evaluating Syndrome Differentiation and Treatment in large language models
  148. Radiologist Copilot: An Agentic Framework Orchestrating Specialized Tools for Reliable Radiology Reporting
  149. Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents
  150. Phase-Adaptive LLM Framework with Multi-Stage Validation for Construction Robot Task Allocation: A Systematic Benchmark Against Traditional Optimization Algorithms
  151. HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval
  152. Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
  153. TrackNetV5: Residual-Driven Spatio-Temporal Refinement and Motion Direction Decoupling for Fast Object Tracking
  154. Perception of AI-Generated Music -- The Role of Composer Identity, Personality Traits, Music Preferences, and Perceived Humanness
  155. LumiX: Structured and Coherent Text-to-Intrinsic Generation
  156. Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset
  157. AI-Driven Document Redaction in UK Public Authorities: Implementation Gaps, Regulatory Challenges, and the Human Oversight Imperative
  158. Towards Unification of Hallucination Detection and Fact Verification for Large Language Models
  159. PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models
  160. SurveyEval: Towards Comprehensive Evaluation of LLM-Generated Academic Surveys
  161. AttMetNet: Attention-Enhanced Deep Neural Network for Methane Plume Detection in Sentinel-2 Satellite Imagery
  162. Adversarial Jamming for Autoencoder Distribution Matching
  163. Probabilistic energy profiler for statically typed JVM-based programming languages
  164. Beyond Paired Data: Self-Supervised UAV Geo-Localization from Reference Imagery Alone
  165. A Framework for Causal Concept-based Model Explanations
  166. Self-Improving AI Agents through Self-Play
  167. AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping
  168. Credal Graph Neural Networks
  169. Generative modeling using evolved quantum Boltzmann machines
  170. StockMem: An Event-Reflection Memory Framework for Stock Forecasting
  171. Menta: A Small Language Model for On-Device Mental Health Prediction
  172. Training Data Attribution for Image Generation using Ontology-Aligned Knowledge Graphs
  173. Empirical Assessment of the Perception of Software Product Line Engineering by an SME before Migrating its Code Base
  174. FGC-Comp: Adaptive Neighbor-Grouped Attribute Completion for Graph-based Anomaly Detection
  175. Conformal Correction for Efficiency May be at Odds with Entropy
  176. A method for tissue-mask supported whole-body image registration in the UK Biobank
  177. GeoBridge++: Fact-Guided Geo-Semantic Bridging for Unified Cross-View Geo-Localization
  178. ALDI-ray: Adapting the ALDI Framework for Security X-ray Object Detection
  179. Embedding networks with the random walk first return time distribution
  180. An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation
  181. ClimaOoD: Improving Anomaly Segmentation via Physically Realistic Synthetic Data
  182. Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance
  183. Exploring Depth Generalization in Large Language Models for Solving Recursive Logic Tasks
  184. SAND Challenge: Four Approaches for Dysartria Severity Classification
  185. UAUTrack: Towards Unified Multimodal Anti-UAV Visual Tracking
  186. Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization
  187. PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes
  188. Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation
  189. Adaptive Weighted LSSVM for Multi-View Classification
  190. Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
  191. Real-Time Multimodal Data Collection Using Smartwatches and Its Visualization in Education
  192. Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
  193. PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking
  194. Leveraging Large-Scale Pretrained Spatial-Spectral Priors for General Zero-Shot Pansharpening
  195. Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
  196. Adapting Tensor Kernel Machines to Enable Efficient Transfer Learning for Seizure Detection
  197. CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography
  198. Content-Aware Texturing for Gaussian Splatting
  199. Modeling and Inverse Identification of Interfacial Heat Conduction in Finite Layer and Semi-Infinite Substrate Systems via a Physics-Guided Neural Framework
  200. Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction
  201. IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai
  202. Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System
  203. EZYer: A simulacrum of high school with generative agent
  204. Empathy Level Prediction in Multi-Modal Scenario with Supervisory Documentation Assistance
  205. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
  206. ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce
  207. OmniPerson: Unified Identity-Preserving Pedestrian Generation
  208. From Veracity to Diffusion: Adressing Operational Challenges in Moving From Fake-News Detection to Information Disorders
  209. Sparse Computations in Deep Learning Inference
  210. Tensor Network Based Feature Learning Model
  211. AVGGT: Rethinking Global Attention for Accelerating VGGT
  212. Laplace Approximation For Tensor Train Kernel Machines In System Identification
  213. A Concise Review of Hallucinations in LLMs and their Mitigation
  214. On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection
  215. Decentralized Fairness Aware Multi Task Federated Learning for VR Network
  216. Two-Stage Vision Transformer for Image Restoration: Colorization Pretraining + Residual Upsampling
  217. Water Quality Estimation Through Machine Learning Multivariate Analysis
  218. AskNearby: An LLM-Based Application for Neighborhood Information Retrieval and Personalized Cognitive-Map Recommendations
  219. A Large Scale Benchmark for Test Time Adaptation Methods in Medical Image Segmentation
  220. Attention-guided reference point shifting for Gaussian-mixture-based partial point set registration
  221. Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing
  222. A Fully First-Order Layer for Differentiable Optimization
  223. Stress-Testing Causal Claims via Cardinality Repairs
  224. Hybrid(Penalized Regression and MLP) Models for Outcome Prediction in HDLSS Health Data
  225. G-SHARP: Gaussian Surgical Hardware Accelerated Real-time Pipeline
  226. Q-BERT4Rec: Quantized Semantic-ID Representation Learning for Multimodal Recommendation
  227. Guided Self-Evolving LLMs with Minimal Human Supervision
  228. scCluBench: Comprehensive Benchmarking of Clustering Algorithms for Single-Cell RNA Sequencing
  229. TGDD: Trajectory Guided Dataset Distillation with Balanced Distribution
  230. TabGRU: An Enhanced Design for Urban Rainfall Intensity Estimation Using Commercial Microwave Links
  231. Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
  232. ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation
  233. HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild
  234. nuScenes Revisited: Progress and Challenges in Autonomous Driving
  235. Temporal Dynamics Enhancer for Directly Trained Spiking Object Detectors
  236. MetaJoin: Adaptive Join Selections for Heterogeneous Tables
  237. Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
  238. LightHCG: a Lightweight yet powerful HSIC Disentanglement based Causal Glaucoma Detection Model framework
  239. Quantum feature encoding optimization
  240. Leveraging Large Language Models to Bridge Cross-Domain Transparency in Stablecoins
  241. Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation
  242. Dynamic Configuration of On-Street Parking Spaces using Multi Agent Reinforcement Learning
  243. ESACT: An End-to-End Sparse Accelerator for Compute-Intensive Transformers via Local Similarity
  244. TaleFrame: An Interactive Story Generation System with Fine-Grained Control and Large Language Models
  245. Nav-R2 Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation
  246. Reproducing and Extending RaDelft 4D Radar with Camera-Assisted Labels
  247. From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
  248. Synthetic Error Injection Fails to Elicit Self-Correction In Language Models
  249. On-the-fly Feedback SfM: Online Explore-and-Exploit UAV Photogrammetry with Incremental Mesh Quality-Aware Indicator and Predictive Path Planning
  250. SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains
  251. Tackling Tuberculosis: A Comparative Dive into Machine Learning for Tuberculosis Detection
  252. Memory-Augmented Knowledge Fusion with Safety-Aware Decoding for Domain-Adaptive Question Answering
  253. WSCF-MVCC: Weakly-supervised Calibration-free Multi-view Crowd Counting
  254. A multi-weight self-matching visual explanation for cnns on sar images
  255. Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
  256. TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction
  257. Forecasting MBTA Transit Dynamics: A Performance Benchmarking of Statistical and Machine Learning Models
  258. Molecular Embedding-Based Algorithm Selection in Protein-Ligand Docking
  259. Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation
  260. Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training
  261. When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers
  262. Training Dynamics of Learning 3D-Rotational Equivariance
  263. Breast Cell Segmentation Under Extreme Data Constraints: Quantum Enhancement Meets Adaptive Loss Stabilization
  264. HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models
  265. VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
  266. Enhancing Cross Domain SAR Oil Spill Segmentation via Morphological Region Perturbation and Synthetic Label-to-SAR Generation