mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 10 Dec 2025

323 papers

  1. PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile DevicesRetrieval-augmented generation → Generation and context integration +1
  2. Complexity Agnostic Recursive Decomposition of ThoughtsLLM reasoning → Test-time compute and efficient thinking
  3. Visual Species Recognition with Large Multimodal Models as Post-Hoc CorrectorsMultimodal LLMs / vision-language models → Agricultural vision-language models
  4. LLaDA2.0: Scaling Up Diffusion Language Models to 100BDiffusion models → Discrete and text diffusion +1
  5. Causal Strengths and Leaky Beliefs: Interpreting LLM Reasoning via Noisy-OR Causal Bayes NetsLLM reasoning → Reasoning benchmarks and evaluation
  6. Structured Personalization: Modeling Constraints as Matroids for Data-Minimal LLM AgentsLLM agents and tool use → Agent memory systems
  7. Mirror Mode in Fire Emblem: Beating Players at their own Game with Imitation and Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
  8. Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  9. Rethinking Query Optimization for Multi-Agent Systems [Vision]LLM reasoning → Reasoning for agents, planning and code +1
  10. SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  11. MedBioRAG: Semantic Search and Retrieval-Augmented Generation with Large Language Models for Medical and Biological QARetrieval-augmented generation → Medical and biomedical RAG
  12. Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual LearningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  13. AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural AdviceRetrieval-augmented generation → Time series and agricultural RAG
  14. Phishing Email Detection Using Large Language ModelsLLM safety and security → Prompt injection and agent security
  15. Push Smarter, Not Harder: Hierarchical RL-Diffusion Policy for Efficient Nonprehensile ManipulationDiffusion models → Diffusion and flow policies for robotics +1
  16. Interpretable Embeddings with Sparse Autoencoders: A Data Analysis ToolkitMechanistic interpretability → SAE features and their applications
  17. What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  18. Independent Density EstimationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  19. Detailed balance in large language model-driven agentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction EstimationDeep reinforcement learning methods → RL theory and sample complexity
  21. MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical MetadataDiffusion models → Medical imaging and segmentation
  22. Intelligently Weighting Multiple Reference Models for Direct Preference Optimization of LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  23. Diffusion Is Your Friend in Show, Suggest and TellDiffusion models → Image generation, text-to-image and editing
  24. Latent Action World Models for Control with Unlabeled TrajectoriesWorld models → Embodied and robot world models +1
  25. GoodSpeed: Optimizing Fair Goodput with Adaptive Speculative Decoding in Distributed Edge InferenceEfficient LLM inference and serving → Speculative decoding
  26. Closing the Train-Test Gap in World Models for Gradient-Based PlanningWorld models → Latent predictive world models
  27. HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action ModelsVision-language-action models → World model-based VLA
  28. Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  29. GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View CapturesDiffusion models → 3D, point cloud and scene generation
  30. Towards Reason-Informed Video Editing in Unified Models with Self-Reflective LearningLLM reasoning → Multimodal reasoning +1
  31. Splatent: Splatting Diffusion Latents for Novel View SynthesisDiffusion models → 3D, point cloud and scene generation
  32. STACHE: Local Black-Box Explanations for Reinforcement Learning PoliciesDeep reinforcement learning methods → Interpretable and logic-guided RL
  33. VisualActBench: Can VLMs See and Act like a Human?Multimodal LLMs / vision-language models → Video understanding with MLLMs
  34. HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model CompressionKnowledge distillation → General knowledge distillation methods
  35. FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement LearningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  36. Diffusion Posterior Sampler for Hyperspectral Unmixing with Spectral Variability ModelingDiffusion models → Inverse problems and image restoration
  37. Hierarchy-Aware Multimodal Unlearning for Medical AIMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  38. UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  39. M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural NetworksMixture-of-experts → MoE for time series and graphs
  40. DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural promptingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  41. Circuits, Features, and Heuristics in Molecular TransformersMechanistic interpretability → Interpreting biomedical and science models
  42. Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMsLLM safety and security → Backdoor and data poisoning attacks
  43. Training One Model to Master Cross-Level Agentic Actions via Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  44. Exqutor: Extended Query Optimizer for Vector-augmented Analytical QueriesRetrieval-augmented generation → RAG pipeline design and evaluation
  45. Unconsciously Forget: Mitigating Memorization; Without Knowing What is being MemorizedLLM safety and security → Vision-language and text-to-image safety
  46. Understanding Chain-of-Thought Effectiveness in Code Generation: An Empirical and Information-Theoretic AnalysisLLM reasoning → Reasoning for agents, planning and code
  47. d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
  48. Neurosymbolic Information Extraction from Transactional DocumentsKnowledge distillation → Knowledge distillation for LLMs
  49. IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual PromptingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  50. Membership and Dataset Inference Attacks on Large Audio Generative ModelsLLM safety and security → Membership inference attacks
  51. MiraMind: Benchmarking Reliable Mental Health Reasoning beyond Answer AccuracyLLM reasoning → Clinical and biomedical applications
  52. End-to-end PDDL Planning with Hardcoded and Dynamic AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  53. GLaD: Geometric Latent Distillation for Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
  54. FROMAT: Multiview Material Appearance Transfer via Few-Shot Self-Attention AdaptationDiffusion models → 3D, point cloud and scene generation
  55. Rethinking Chain-of-Thought Reasoning for VideosLLM reasoning → Multimodal reasoning +1
  56. Investigate the Low-level Visual Perception in Vision-Language based Image Quality AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
  57. Lazy Diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flowsDiffusion models → Flow matching, time series and science
  58. Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone RacingDeep reinforcement learning methods → RL for robot navigation and UAV control
  59. Building Reasonable Inference for Vision-Language Models in Blind Image Quality AssessmentLLM reasoning → Multimodal reasoning +1
  60. Supporting Dynamic Agentic Workloads: How Data and Agents InteractLLM reasoning → Reasoning for agents, planning and code +1
  61. SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMsLLM agents and tool use → Software engineering coding agents
  62. RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement LearningRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
  63. Color encoding in Latent Space of Stable Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  64. WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  65. Architectures for Building Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
  66. Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and SegmentationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  67. Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  68. Knowledge-Augmented Large Language Model Agents for Explainable Financial Decision-MakingLLM agents and tool use → Financial trading and forecasting agents
  69. ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class AcceleratorsEfficient LLM inference and serving → Serving systems and request scheduling
  70. Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound SynthesisDiffusion models → Medical imaging and segmentation
  71. Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  72. GAIR: GUI Automation via Information-Joint Reasoning and Group ReflectionLLM reasoning → Multimodal reasoning
  73. Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  74. CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  75. Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video UnderstandingLLM reasoning → Multimodal reasoning
  76. TextGuider: Training-Free Guidance for Text Rendering via Attention AlignmentDiffusion models → Image generation, text-to-image and editing
  77. COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement LearningLLM reasoning → Chain-of-thought reasoning for driving +1
  78. Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANNRetrieval-augmented generation → Vector search and ANN indexes
  79. Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein DesignKnowledge distillation → Knowledge distillation for LLMs
  80. ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source DataLLM agents and tool use → Agent threats, guardrails and governance +1
  81. Electric Arc Furnaces Scheduling under Electricity Price Volatility with Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  82. FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation ModelDiffusion models → Inverse problems and image restoration +1
  83. Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not TokensMixture-of-experts → Efficient MoE training and inference systems
  84. Goal inference with Rao-Blackwellized Particle FiltersLLM agents and tool use → General LLM agent frameworks and benchmarks
  85. GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language ModelLLM reasoning → Spatial and embodied reasoning +1
  86. OmniPSD: Layered PSD Generation with Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
  87. Training-free Context-adaptive Attention for Efficient Long Context ModelingEfficient LLM inference and serving → KV cache optimization
  88. Exploratory Mean-Variance with Jumps: An Equilibrium ApproachDeep reinforcement learning methods → Adversarial robustness and RL in finance
  89. CORE: A Conceptual Reasoning Layer for Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  90. View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene GraphsLLM reasoning → Spatial and embodied reasoning
  91. Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  92. One Size Fits None: Modeling NYC Taxi Trips
  93. Qwerty AI: Explainable Automated Age Rating and Content Safety Assessment for Russian-Language Screenplays
  94. Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments
  95. LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach
  96. Network Traffic Analysis with Process Mining: The UPSIDE Case Study
  97. Comparative Evaluation of Explainable Machine Learning Versus Linear Regression for Predicting County-Level Lung Cancer Mortality Rate in the United States
  98. D3G: Diverse Demographic Data Generation Increases Zero-Shot Image Classification Accuracy within Multimodal Models
  99. A Unified Generative-Predictive Framework for Deterministic Inverse Design
  100. How Do Graph Signals Affect Recommendation: Unveiling the Mystery of Low and High-Frequency Graph Signals
All 323
  1. Prompt-to-Parts: Generative AI for Physical Assembly and Scalable Instructions
  2. SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
  3. INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT
  4. Semantic Geometry for policy-constrained interpretation
  5. A data-driven approach to inferring travel trajectory during peak hours in urban rail transit systems
  6. MPath: Multimodal Pathology Report Generation from Whole Slide Images
  7. Smartphone monitoring of smiling as a behavioral proxy of well-being in everyday life
  8. Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamics
  9. CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
  10. Microscopic Vehicle Trajectory Datasets from UAV-collected Video for Heterogeneous, Area-Based Urban Traffic
  11. Hot H'em: S`ai G`on Gi~ua C'ai N'ong Hong C`ong B`ang -- Saigon in Unequal Heat
  12. mmWEAVER: Environment-Specific mmWave Signal Synthesis from a Photo and Activity Description
  13. Beyond Memristor: Neuromorphic Computing Using Meminductor
  14. Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality
  15. KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
  16. Boosted Random Forests for Predicting Treatment Failure of Chemotherapy Regimens
  17. STARK denoises spatial transcriptomics images via adaptive regularization
  18. Enhancing Large Language Model-Based Systems for End-to-End Circuit Analysis Problem Solving
  19. Inference for Batched Adaptive Experiments
  20. Rethinking Bivariate Causal Discovery Through the Lens of Exchangeability
  21. Topological Conditioning for Mammography Models via a Stable Wavelet-Persistence Vectorization
  22. STARS: Semantic Tokens with Augmented Representations for Recommendation at Scale
  23. PARAN: Persona-Augmented Review ANswering system on Food Delivery Review Dataset
  24. When do cheap embeddings beat protein language models? A theoretically-grounded hashing sketch for biological sequence classification
  25. Sequence-to-Image Transformation for Sequence Classification Using Rips Complex Construction and Chaos Game Representation
  26. Partitioning the Sample Space for a More Precise Shannon Entropy Estimation
  27. Universal Hirschberg for Width Bounded Dynamic Programs
  28. A Model-Guided Neural Network Method for the Inverse Scattering Problem
  29. Workflow is All You Need: Escaping the "Statistical Smoothing Trap" via High-Entropy Information Foraging and Adversarial Pacing
  30. VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio
  31. CHyLL: Learning Continuous Neural Representations of Hybrid Systems
  32. Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models
  33. Belief Is All You Need: Modeling Narrative Archetypes in Conspiratorial Discourse
  34. Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information
  35. Robust AI Security and Alignment: A Sisyphean Endeavor?
  36. MedXAI: A Retrieval-Augmented and Self-Verifying Framework for Knowledge-Guided Medical Image Analysis
  37. TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracing
  38. Defining the Scope of Learning Analytics: An Axiomatic Approach for Analytic Practice and Measurable Learning Phenomena
  39. Classifying Metamorphic versus Single-Fold Proteins with Statistical Learning and AlphaFold2
  40. Linear socio-demographic representations emerge in Large Language Models from indirect cues
  41. Text2Graph: Combining Lightweight LLMs and GNNs for Efficient Text Classification in Label-Scarce Scenarios
  42. Mind the Gap! Pathways Towards Unifying AI Safety and Ethics Research
  43. Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens
  44. Parallel Decoder Transformer: Planner-Conditioned Latent Coordination for Model-Intrinsic Parallel Generation
  45. LxCIM: a new rank-based binary classifier performance metric invariant to local exchange of classes
  46. DB2-TransF: All You Need Is Learnable Daubechies Wavelets for Time Series Forecasting
  47. SimWorld-Robotics: Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
  48. Local LLM Ensembles for Zero-shot Portuguese Named Entity Recognition
  49. DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations
  50. Robust Gradient Descent via Heavy-Ball Momentum with Predictive Extrapolation
  51. Cluster-Dags as Powerful Background Knowledge For Causal Discovery
  52. ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects
  53. Exploring LLMs for Scientific Information Extraction Using The SciEx Framework
  54. Fuzzy Hierarchical Multiplex
  55. Enhancing Fake-News Detection with Node-Level Topological Features
  56. AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
  57. Neuromorphic Eye Tracking for Low-Latency Pupil Detection
  58. TDC-Cache: A Trustworthy Decentralized Cooperative Caching Framework for Web3.0
  59. LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating
  60. FALCON: Few-step Accurate Likelihoods for Continuous Flows
  61. NordFKB: a fine-grained benchmark dataset for geospatial AI in Norway
  62. Supervised learning pays attention
  63. Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach
  64. Bayesian Networks, Markov Networks, Moralisation, Triangulation: a Categorical Perspective
  65. YOPO-Nav: Visual Navigation using 3DGS Graphs from One-Pass Videos
  66. Visual Heading Prediction for Autonomous Aerial Vehicles
  67. SCOPE: Language Models as One-Time Teacher for Hierarchical Planning in Text Environments
  68. Human-in-the-Loop and AI: Crowdsourcing Metadata Vocabulary for Materials Science
  69. Exploring Protein Language Model Architecture-Induced Biases for Antibody Comprehension
  70. Provably Learning from Modern Language Models via Low Logit Rank
  71. Analysis of Dirichlet Energies as Over-smoothing Measures
  72. Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
  73. Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs
  74. Mitigating Social Bias in English and Urdu Language Models Using PRM-Guided Candidate Selection and Sequential Refinement
  75. New Approximation Results and Optimal Estimation for Fully Connected Deep Neural Networks
  76. Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation
  77. Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability
  78. From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities
  79. ChronusOmni: Improving Time Awareness of Omni Large Language Models
  80. Fast Factorized Learning: Powered by In-Memory Database Systems
  81. Predicting the Containment Time of California Wildfires Using Machine Learning
  82. Interpretation as Linear Transformation: A Cognitive-Geometric Model of Concepts and Meaning
  83. LLMs in Interpreting Legal Documents
  84. RIFT: A Scalable Methodology for LLM Accelerator Fault Assessment using Reinforcement Learning
  85. Composing Concepts from Images and Videos via Concept-prompt Binding
  86. Geospatial Soil Quality Analysis: A Roadmap for Integrated Systems
  87. Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation
  88. Incorporating Fairness in Neighborhood Graphs for Fair Spectral Clustering
  89. CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing
  90. OnCoCo 1.0: A Public Dataset for Fine-Grained Message Classification in Online Counseling Conversations
  91. Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation
  92. Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers
  93. Knowledge Diversion for Efficient Morphology Control and Policy Transfer
  94. FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation
  95. TinyD'ej`aVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams
  96. Predicting Polymer Solubility in Solvents Using SMILES Strings
  97. Physics-Aware Heterogeneous GNN Architecture for Real-Time BESS Optimization in Unbalanced Distribution Systems
  98. PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation
  99. Optimal certification of constant-local Hamiltonians
  100. Quantifying Uncertainty in Machine Learning-Based Pervasive Systems: Application to Human Activity Recognition
  101. Stylized Meta-Album: Group-bias injection with style transfer to study robustness against distribution shifts
  102. MOA: Multi-Objective Alignment for Role-Playing Agents
  103. Analyzing Planner Design Trade-offs for MAPF under ADG-based Realistic Execution
  104. Interpreto: An Explainability Library for Transformers
  105. Ethics Readiness of Artificial Intelligence: A Practical Evaluation Method
  106. Gaussian Process Aggregation for Root-Parallel Monte Carlo Tree Search with Continuous Actions
  107. Mixture of Lookup Key-Value Experts
  108. FineFreq: A Multilingual Character Frequency Dataset from Web-Scale Text
  109. LiM-YOLO: Less is More with Pyramid Level Shift for Ship Detection in Optical Remote Sensing
  110. A data-driven approach to linking design features with manufacturing process data for sustainable product development
  111. Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies
  112. Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization
  113. Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power
  114. An Automated Tip-and-Cue Framework for Optimized Satellite Tasking and Visual Intelligence
  115. OxEnsemble: Fair Ensembles for Low-Data Classification
  116. SynthPix: A lightspeed PIV image generator
  117. Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection
  118. VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification
  119. Kaapana: A Comprehensive Open-Source Platform for Integrating AI in Medical Imaging Research Environments
  120. Creation of the Estonian Subjectivity Dataset: Assessing the Degree of Subjectivity on a Scale
  121. Benchmarking SAM2-based Trackers on FMOX
  122. Beyond Sequences: A Benchmark for Atomic Hand-Object Interaction Using a Static RNN Encoder
  123. Semantic-Aware Cooperative Communication and Computation Framework in Vehicular Networks
  124. ImageTalk: Designing a Multimodal AAC Text Generation System Driven by Image Recognition and Natural Language Generation
  125. UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
  126. CS3D: An Efficient Facial Expression Recognition via Event Vision
  127. Stanford Sleep Bench: Evaluating Polysomnography Pre-training Methods for Sleep Foundation Models
  128. Graph-Based Bayesian Optimization for Quantum Circuit Architecture Search with Uncertainty Calibrated Surrogates
  129. UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision
  130. Content-Adaptive Image Retouching Guided by Attribute-Based Text Representation
  131. Hands-on Evaluation of Visual Transformers for Object Recognition and Detection
  132. Auto-BenchmarkCard: Automated Synthesis of Benchmark Documentation
  133. Seeing Soil from Space: Towards Robust and Scalable Remote Soil Nutrient Analysis
  134. The Gender Code: Gendering the Global Governance of Artificial Intelligence
  135. Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Search
  136. From Graphs to Gates: DNS-HyXNet, A Lightweight and Deployable Sequential Model for Real-Time DNS Tunnel Detection
  137. System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection
  138. Systematic Framework of Application Methods for Large Language Models in Language Sciences
  139. A Dual-Domain Convolutional Network for Hyperspectral Single-Image Super-Resolution
  140. Comparative Analysis of Hash-based Malware Clustering via K-Means
  141. Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
  142. Latent-Autoregressive GP-VAE Language Model
  143. Transformers for Tabular Data: A Training Perspective of Self-Attention via Optimal Transport
  144. Masked Registration and Autoencoding of CT Images for Predictive Tibia Reconstruction
  145. NeuroSketch: A Practical Design Recipe for Neural Decoding
  146. QuanvNeXt: An end-to-end quanvolutional neural network for EEG-based detection of major depressive disorder
  147. Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
  148. Contextual Dynamic Pricing with Heterogeneous Buyers
  149. ViTA-Seg: Vision Transformer for Amodal Segmentation in Robotics
  150. Estimation of Stochastic Optimal Transport Maps
  151. Gradient-Guided Learning Network for Infrared Small Target Detection
  152. Representation Invariance and Allocation: When Subgroup Balance Matters
  153. StateSpace-SSL: Linear-Time Self-supervised Learning for Plant Disease Detection
  154. MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images
  155. Advancing LLM-Based Security Automation with Customized Group Relative Policy Optimization for Zero-Touch Networks
  156. Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines
  157. Temporal-Spatial Tubelet Embedding for Cloud-Robust MSI Reconstruction using MSI-SAR Fusion: A Multi-Head Self-Attention Video Vision Transformer Approach
  158. LiePrune: Lie Group and Quantum Geometric Dual Representation for One-Shot Structured Pruning of Quantum Neural Networks
  159. Cauchy-Schwarz Fairness Regularizer
  160. Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturing
  161. Cytoplasmic Strings Analysis in Human Embryo Time-Lapse Videos using Deep Learning Framework
  162. Calibrated Keyframe-Segment Selection for Descriptor-Agnostic LiDAR Loop Closure in Repetitive Environments
  163. Advancing Text Classification with Large Language Models and Neural Attention Mechanisms
  164. A Human-AI Collaborative Workflow for Mathematical Discovery: A Case Study in Grover-Compatible Riemannian Optimization
  165. UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents
  166. CourtPressGER: A German Court Decision to Press Release Summarization Dataset
  167. FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds
  168. InfoMotion: A Graph-Based Approach to Video Dataset Distillation for Echocardiography
  169. DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluation
  170. Generalizable Collaborative Search-and-Capture in Cluttered Environments via Path-Guided MAPPO and Directional Frontier Allocation
  171. Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration
  172. H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
  173. Wasserstein-Aligned Hyperbolic Multi-View Clustering
  174. Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting
  175. Language models as tools for investigating the distinction between possible and impossible natural languages
  176. Detection and Localization of Subdural Hematoma Using Deep Learning on Computed Tomography
  177. CONCUR: A Framework for Continual Constrained and Unconstrained Routing
  178. BugSweeper: Function-Level Detection of Smart Contract Vulnerabilities Using Graph Neural Networks
  179. Perception-Inspired Color Space Design for Photo White Balance Editing
  180. Personalized Federated Distillation Assisted Vehicle Edge Caching Strategy
  181. Rates and architectures for learning geometrically non-trivial operators
  182. Log NeRF: Comparing Spaces for Learning Radiance Fields
  183. FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)N Diffusion Refinement
  184. Meta-learning three-factor plasticity rules for structured credit assignment with sparse feedback
  185. KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction
  186. ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance Segmentation
  187. StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation
  188. A Granular Framework for Construction Material Price Forecasting: Econometric and Machine-Learning Approaches
  189. Minimization of Functions on Dually Flat Spaces Using Geodesic Descent Based on Dual Connections
  190. Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
  191. Development and Testing for Perception Based Autonomous Landing of a Long-Range QuadPlane
  192. Visual Categorization Across Minds and Models: Cognitive Analysis of Human Labeling and Neuro-Symbolic Integration
  193. Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Video
  194. Improved Physics-Driven Neural Network to Solve Inverse Scattering Problems
  195. UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
  196. Self-Supervised Learning with Gaussian Processes
  197. Efficiency-Aware Computational Intelligence for Resource-Constrained Manufacturing Toward Edge-Ready Deployment
  198. Simultaneous Genetic Evolution of Neural Networks for Optimal SFC Embedding
  199. Functional Percolation: Criticality of Form and Function
  200. Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook
  201. Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices
  202. Transformer-Driven Multimodal Fusion for Explainable Suspiciousness Estimation in Visual Surveillance
  203. A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edge
  204. From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation
  205. VABench: A Comprehensive Benchmark for Audio-Video Generation
  206. Traffic Scene Small Target Detection Method Based on YOLOv8n-SPTS Model for Autonomous Driving
  207. Distributional Shrinkage II: Higher-Order Scores Encode Brenier Map
  208. Identifying Bias in Machine-generated Text Detection
  209. MelanomaNet: Explainable Deep Learning for Skin Lesion Classification
  210. LoGoColor: Local-Global 3D Colorization for 360deg Scenes
  211. Dynamic Facial Expressions Analysis Based Parkinson's Disease Auxiliary Diagnosis
  212. Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
  213. LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations
  214. MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectional Blending with Hierarchical Densification
  215. Contrastive Learning for Semi-Supervised Deep Regression with Generalized Ordinal Rankings from Spectral Seriation
  216. Robust and Sparse Estimation of Unbounded Density Ratio under Heavy Contamination
  217. FBA2D: Frequency-based Black-box Attack for AI-generated Image Detection
  218. ROI-Packing: Efficient Region-Based Compression for Machine Vision
  219. Debiased Bayesian Inference for High-dimensional Regression Models
  220. A Clinically Interpretable Deep CNN Framework for Early Chronic Kidney Disease Prediction Using Grad-CAM-Based Explainable AI
  221. Efficient Feature Compression for Machines with Global Statistics Preservation
  222. Enabling Next-Generation Consumer Experience with Feature Coding for Machines
  223. Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers