mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 6 Jun 2025

380 papers

  1. Graph Diffusion that can Insert and DeleteDiffusion models → Flow matching, time series and science
  2. MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  3. DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference AccelerationEfficient LLM inference and serving → KV cache optimization
  4. Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive SurveyLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Debiasing Online Preference Learning via Preference Feature PreservationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  6. AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven OptimizationDiffusion models → 3D, point cloud and scene generation
  7. Reinforcement Learning for Autonomous Warehouse Orchestration in SAP Logistics Execution: Redefining Supply Chain AgilityDeep reinforcement learning methods → RL for energy, networks and operations
  8. Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval OutcomesMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  9. Improving LLM-Powered EDA Assistants with RAFTRetrieval-augmented generation → RAG pipeline design and evaluation
  10. SPARQ: Synthetic Problem Generation for Reasoning via Quality-Diversity AlgorithmsLLM reasoning → Mathematical reasoning
  11. Membership Inference Attacks for Unseen ClassesLLM safety and security → Membership inference attacks
  12. A Certified Unlearning Approach without Access to Source DataLLM safety and security → Machine unlearning
  13. The Economic Dispatch of Power-to-Gas Systems with Deep Reinforcement Learning:Tackling the Challenge of Delayed Rewards with Long-Term Energy StorageDeep reinforcement learning methods → RL for energy, networks and operations
  14. Noise Consistency Regularization for Improved Subject-Driven Image SynthesisDiffusion models → Image generation, text-to-image and editing
  15. SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo AugmentationLLM reasoning → Test-time compute and efficient thinking
  16. Towards Infant Sleep-Optimized Driving: Synergizing Wearable and Vehicle Sensing in Intelligent Cruise ControlEnd-to-end autonomous driving → Cooperative and V2X driving
  17. Saffron-1: Safety Inference ScalingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  18. Delphos: A reinforcement learning framework for assisting discrete choice model specificationDeep reinforcement learning methods → RL training of language and agent models
  19. HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token PredictionsLLM safety and security → Watermarking generated content and models
  20. TimeWak: Temporal Chained-Hashing Watermark for Time Series DataDiffusion models → Robustness, privacy and adversarial aspects
  21. SMAR: Soft Modality-Aware Routing Strategy for MoE-based Multimodal Large Language Models Preserving Language CapabilitiesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  22. Unintended Harms of Value-Aligned LLMs: Psychological and Empirical InsightsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  23. CoMemo: LVLMs Need Image Context with Image MemoryMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  24. Distillation Robustifies UnlearningLLM safety and security → Machine unlearning
  25. Movie Facts and Fibs (MF2): A Benchmark for Long Movie UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  26. Cartridges: Lightweight and general-purpose long context representations via self-studyEfficient LLM inference and serving → Prompt and context compression
  27. Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian LensOffline RL and imitation learning from data → Offline RL algorithms +1
  28. PersonaAgent: Bridging Memory and Action for Personalized LLM AgentsLLM agents and tool use → Agent memory systems
  29. Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  30. Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream KnowledgeRetrieval-augmented generation → RAG robustness and adaptive retrieval
  31. Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking StudyMultimodal LLMs / vision-language models → Medical vision-language models
  32. GenIR: Generative Visual Feedback for Mental Image RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  33. STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  34. Can Theoretical Physics Research Benefit from Language Agents?LLM agents and tool use → Web, search, and research agents
  35. PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in PuzzlehuntsLLM reasoning → Reasoning benchmarks and evaluation
  36. How to craft a deep reinforcement learning policy for wind farm flow controlDeep reinforcement learning methods → RL for energy, networks and operations
  37. 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World ModelWorld models → Embodied and robot world models
  38. Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot GeneralizationDiffusion models → Diffusion and flow policies for robotics
  39. Antithetic Noise in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  40. Reusing Trajectories in Policy Gradients Enables Fast ConvergenceDeep reinforcement learning methods → RL theory and sample complexity
  41. Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent ApproachLLM agents and tool use → Multimodal and embodied agents
  42. Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Privacy and security of RAG
  43. Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  44. Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling LibraryLLM reasoning → Reinforcement learning for reasoning +1
  45. Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning CompletenessLLM safety and security → Machine unlearning
  46. VideoChat-A1: Thinking with Long Videos by Chain-of-Shot ReasoningLLM reasoning → Multimodal reasoning
  47. Feedback Guidance of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  48. Self driving algorithm for an active four wheel drive racecarEnd-to-end autonomous driving → Reinforcement learning for driving +1
  49. Full Conformal Adaptation of Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  50. System-Aware Unlearning Algorithms: Use Lesser, Forget FasterLLM safety and security → Machine unlearning
  51. BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  52. MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  53. Restereo: Diffusion stereo video generation and restorationDiffusion models → 3D, point cloud and scene generation
  54. Optimization-Free Universal Watermark Forgery with Regenerative Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  55. AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical SearchLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Unlocking Recursive Thinking of LLMs: Alignment via RefinementLLM reasoning → Test-time compute and efficient thinking +1
  57. Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  58. Can VLMs Predict Future States? Bootstrapping World Models from Inverse DynamicsWorld models → Embodied and robot world models +2
  59. What Really is a Member? Discrediting Membership Inference via PoisoningLLM safety and security → Membership inference attacks
  60. Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  61. CrimeMind: Simulating Urban Crime with Multi-Modal LLM AgentsLLM agents and tool use → Multimodal and embodied agents
  62. AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill DiversificationDeep reinforcement learning methods → Deep RL algorithms and representations
  63. Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  64. Preference Learning for AI Alignment: a Causal PerspectiveLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  65. AQUATIC-Diff: Additive Quantization for Truly Tiny Compressed Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  66. Learning Deterministic Policies with Policy Gradients in Constrained Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
  67. Exponential Family Variational Flow Matching for Tabular Data GenerationDiffusion models → Flow matching, time series and science
  68. Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  69. DynamicMind: A Tri-Mode Thinking System for Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  70. FADE: Frequency-Aware Diffusion Model Factorization for Video EditingDiffusion models → Video generation
  71. MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language ModelsMixture-of-experts → Mixture of LoRA experts
  72. Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model RouterLLM reasoning → Test-time compute and efficient thinking
  73. Object Navigation with Structure-Semantic Reasoning-Based Multi-level Map and Multimodal Decision-Making LLMLLM reasoning → Spatial and embodied reasoning
  74. Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
  75. HMVLM: Multistage Reasoning-Enhanced Vision-Language Model for Long-Tailed Driving ScenariosLLM reasoning → Chain-of-thought reasoning for driving +2
  76. Human-AI Alignment of Multimodal Large Language Models with Speech-Language Pathologists in Parent-Child InteractionsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  77. Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  78. FontAdapter: Instant Font Adaptation in Visual Text GenerationDiffusion models → Image generation, text-to-image and editing
  79. FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and ChallengingLLM reasoning → Reasoning for agents, planning and code
  80. CodeContests+: High-Quality Test Case Generation for Competitive ProgrammingLLM reasoning → Reasoning for agents, planning and code
  81. MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  82. Where Do Humans Look When Demonstrating to Robots? Human Gaze Behavior in Pick-and-Place Tasks Across Demonstration DevicesOffline RL and imitation learning from data → Robot manipulation imitation learning
  83. LLIA -- Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion ModelsDiffusion models → Audio, speech and music
  84. Discrete Minds in a Continuous World: Do Language Models Know Time Passes?LLM reasoning → Knowledge- and tool-augmented reasoning
  85. Evaluating Neuron Explanations: A Unified Framework with Sanity ChecksMechanistic interpretability → Circuits and mechanistic analysis
  86. dots.llm1 Technical ReportMixture-of-experts → MoE large language models
  87. BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular InteractionsLLM reasoning → Clinical and biomedical applications +1
  88. Do Large Vision-Language Models Distinguish between the Actual and Apparent Features of Illusions?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  89. BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  90. Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  91. FlowOE: Imitation Learning with Flow Policy from Ensemble RL Experts for Optimal Execution under Heston Volatility and Concave Market ImpactsDiffusion models → Flow matching, time series and science +1
  92. Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art PerformanceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  93. LLM-Symbolic Integration for Robust Temporal Tabular ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  94. SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  95. Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph PropertiesLLM reasoning → Knowledge- and tool-augmented reasoning
  96. When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive LearningLLM safety and security → Membership inference attacks
  97. To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic PromptLLM agents and tool use → Agent threats, guardrails and governance +1
  98. Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence AwarenessLLM safety and security → Machine unlearning
  99. Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  100. Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to ApplicationDiffusion models → Diffusion for compression and wireless
All 380
  1. Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer AccelerationEfficient LLM inference and serving → Token pruning and merging for ViTs
  2. MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations TheoryMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  3. Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning FrameworkKnowledge distillation → Knowledge distillation for LLMs
  4. When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  5. Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  6. Learning Design-Score Manifold to Guide Diffusion Models for Offline OptimizationDiffusion models → Diffusion foundations and sampling
  7. Numerical Investigation of Sequence Modeling Theory using Controllable Memory FunctionsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  8. RNE: plug-and-play diffusion inference-time control and energy-based trainingDiffusion models → Diffusion foundations and sampling
  9. DriveAction: A Benchmark for Exploring Human-like Driving Decisions in VLA ModelsVision-language-action models → VLA for autonomous driving +1
  10. GAITEX: Human motion dataset of impaired gait and rehabilitation exercises using inertial and optical sensors
  11. ChatMyopia: An AI Agent for Pre-consultation Education in Primary Eye Care Settings
  12. Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
  13. Differentiable neural network representation of multi-well, locally-convex potentials
  14. Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks
  15. A Synthetic Pseudo-Autoencoder Invites Examination of Tacit Assumptions in Neural Network Design
  16. T-TExTS (Teaching Text Expansion for Teacher Scaffolding): Enhancing Text Selection in High School Literature through Knowledge Graph-Based Recommendation
  17. You Only Fine-tune Once: Many-Shot In-Context Fine-Tuning for Large Language Models
  18. An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron Diffractometry
  19. Knowledge Graph Embeddings with Representing Relations as Annular Sectors
  20. C-SEO Bench: Does Conversational SEO Work?
  21. Assessing the Impact of Anisotropy in Neural Representations of Speech: A Case Study on Keyword Spotting
  22. Persistent Homology of Topic Networks for the Prediction of Reader Curiosity
  23. The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
  24. A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations
  25. Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery
  26. EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model
  27. Neural-Augmented Kelvinlet for Real-Time Soft Tissue Deformation Modeling
  28. The World of AI: A Novel Approach to AI Literacy for First-year Engineering Students
  29. E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time
  30. Precise Information Control in Long-Form Text Generation
  31. Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures
  32. Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing
  33. AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecture
  34. Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
  35. A Deep Learning Approach for Facial Attribute Manipulation and Reconstruction in Surveillance and Reconnaissance
  36. Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce
  37. The Optimization Paradox in Clinical AI Multi-Agent Systems
  38. Graph Persistence goes Spectral
  39. Textile Analysis for Recycling Automation using Transfer Learning and Zero-Shot Foundation Models
  40. AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
  41. Securing Traffic Sign Recognition Systems in Autonomous Vehicles
  42. LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles
  43. Rapid training of Hamiltonian graph networks using random features
  44. Infinity Search: Approximate Vector Search with Projections on q-Metric Spaces
  45. SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networks
  46. GeoClip: Geometry-Aware Clipping for Differentially Private SGD
  47. Direct Fisher Score Estimation for Likelihood Maximization
  48. KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
  49. Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches
  50. Beyond Facts: Evaluating Intent Hallucination in Large Language Models
  51. Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models
  52. Hierarchical and Collaborative LLM-Based Control for Multi-UAV Motion and Communication in Integrated Terrestrial and Non-Terrestrial Networks
  53. ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search
  54. Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
  55. Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
  56. A Systematic Review of Poisoning Attacks Against Large Language Models
  57. GS4: Generalizable Sparse Splatting Semantic SLAM
  58. Private GPTs for LLM-driven testing in software development and machine learning
  59. InstantFT: An FPGA-Based Runtime Subsecond Fine-tuning of CNN Models
  60. Optimal Rates in Continual Linear Regression via Increasing Regularization
  61. Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
  62. Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict
  63. TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
  64. (LiFT) Lightweight Fitness Transformer: A language-vision model for Remote Monitoring of Physical Training
  65. Edge-Enabled Collaborative Object Detection for Real-Time Multi-Vehicle Perception
  66. Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
  67. Splat and Replace: 3D Reconstruction with Repetitive Elements
  68. WISCA: A Consensus-Based Approach to Harmonizing Interpretability in Tabular Datasets
  69. LETS Forecast: Learning Embedology for Time Series Forecasting
  70. Tokenization Multiplicity Leads to Arbitrary Price Variation in LLM-as-a-service
  71. Superior Molecular Representations from Intermediate Encoder Layers
  72. Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
  73. Data-Driven High-Dimensional Statistical Inference with Generative Models
  74. Benchmarking Misuse Mitigation Against Covert Adversaries
  75. NeurNCD: Novel Class Discovery via Implicit Neural Representation
  76. CoxNTF: A New Approach for Joint Clustering and Prediction in Survival Analysis
  77. Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs
  78. ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstruction
  79. TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
  80. Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
  81. ExAct: A Video-Language Benchmark for Expert Action Analysis
  82. STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
  83. AdvSumm: Adversarial Training for Bias Mitigation in Text Summarization
  84. BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading
  85. An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
  86. Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision
  87. Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems
  88. DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
  89. Lagrangian-based Equilibrium Propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian Echo Learning
  90. Neural Responses to Affective Sentences Reveal Signatures of Depression
  91. Fairmetrics: An R package for group fairness evaluation
  92. Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection
  93. Optimizing Cloud-to-GPU Throughput for Deep Learning With Earth Observation Data
  94. Towards an Explainable Comparison and Alignment of Feature Embeddings
  95. "We need to avail ourselves of GenAI to enhance knowledge distribution": Empowering Older Adults through GenAI Literacy
  96. BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly
  97. Integer Linear Programming Preprocessing for Maximum Satisfiability
  98. Corrector Sampling in Language Models
  99. Model-Driven Graph Contrastive Learning
  100. Building Models of Neurological Language
  101. Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
  102. MLOps with Microservices: A Case Study on the Maritime Domain
  103. Transformative or Conservative? Conservation laws for ResNets and Transformers
  104. ICU-TSB: A Benchmark for Temporal Patient Representation Learning for Unsupervised Stratification into Patient Cohorts
  105. Physics-Informed Neural Networks for Control of Single-Phase Flow Systems Governed by Partial Differential Equations
  106. Detecting Voice Phishing with Precision: Fine-Tuning Small Language Models
  107. A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
  108. SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery
  109. Technical Report for Egocentric Mistake Detection for the HoloAssist Challenge
  110. semantic-features: A User-Friendly Tool for Studying Contextual Word Embeddings in Interpretable Semantic Spaces
  111. The Lock-in Hypothesis: Stagnation by Algorithm
  112. (AI peers) are people learning from the same standpoint: Perception of AI characters in a Collaborative Science Investigation
  113. Recommender systems, stigmergy, and the tyranny of popularity
  114. ENMA: Tokenwise Autoregression for Generative Neural PDE Operators
  115. Masked Language Models are Good Heterogeneous Graph Generalizers
  116. Fine-grained Hierarchical Crop Type Classification from Integrated Hyperspectral EnMAP Data and Multispectral Sentinel-2 Time Series: A Large-scale Dataset and Dual-stream Transformer Method
  117. CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
  118. carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
  119. Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Time Scales
  120. Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition
  121. Gradient Similarity Surgery in Multi-Task Deep Learning
  122. CCLSTM: Coupled Convolutional Long-Short Term Memory Network for Occupancy Flow Forecasting
  123. Flow-Attentional Graph Neural Networks
  124. Convergence of linear programming hierarchies for Gibbs states of spin systems
  125. Decomposability-Guided Cooperative Coevolution for Large-Scale Itinerary Planning
  126. Bidirectional Image-Event Guided Fusion Framework for Low-Light Image Enhancement
  127. Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction
  128. Scalable unsupervised feature selection via weight stability
  129. Bridging the Gap: In-Context Learning for Modeling Human Disagreement
  130. Synthetic Tabular Data: Methods, Attacks and Defenses
  131. Text-to-LoRA: Instant Transformer Adaption
  132. WoundAIssist: Development and Evaluation of an AI-Based Mobile Application for Remote Chronic Wound Care in Elderly Patients
  133. DermaCon-IN: A Multi-concept Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI Research
  134. Label-Context-Dependent Internal Language Model Estimation for CTC
  135. Accelerating Sparse Transformer Inference on GPU
  136. Onboard Mission Replanning for Adaptive Cooperative Multi-Robot Systems
  137. Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning
  138. LinGuinE: Longitudinal Guidance Estimation for Volumetric Tumour Segmentation
  139. MIRIAD: Augmenting LLMs with millions of medical query-response pairs
  140. Multilevel neural simulation-based inference
  141. WisWheat: A Three-Tiered Vision-Language Dataset for Wheat Management
  142. A Novel, Human-in-the-Loop Computational Grounded Theory Framework for Big Social Data
  143. CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition
  144. Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning
  145. Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
  146. Microgrids Coalitions for Energy Market Balancing
  147. Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
  148. FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound
  149. DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problems
  150. TRUST: Test-time Resource Utilization for Superior Trustworthiness
  151. Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
  152. SDS-Net: Shallow-Deep Synergism-detection Network for infrared small target detection
  153. Tensor-to-Tensor Models with Fast Iterated Sum Features
  154. Do-PFN: In-Context Learning for Causal Effect Estimation
  155. HAVIR: HierArchical Vision to Image Reconstruction using CLIP-Guided Versatile Diffusion
  156. Large Language Models are Demonstration Pre-Selectors for Themselves
  157. End-to-End Framework for Robot Lawnmower Coverage Path Planning using Cellular Decomposition
  158. Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
  159. O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
  160. On Inverse Problems, Parameter Estimation, and Domain Generalization
  161. Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
  162. When to Trust Context: Self-Reflective Debates for Context Reliability
  163. Enhancing Orthopox Image Classification Using Hybrid Machine Learning and Deep Learning Models
  164. LightGTS: A Lightweight General Time Series Forecasting Model
  165. LaDEEP: A Deep Learning-based Surrogate Model for Large Deformation of Elastic-Plastic Solids
  166. Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system
  167. RETENTION: Resource-Efficient Tree-Based Ensemble Model Acceleration with Content-Addressable Memory
  168. A Culturally-Rich Romanian NLP Dataset from "Who Wants to Be a Millionaire?" Videos
  169. Leveraging Generative AI for Enhancing Automated Assessment in Programming Education Contests
  170. Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
  171. Audio-Aware Large Language Models as Judges for Speaking Styles
  172. MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks
  173. Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization
  174. Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
  175. LTG at SemEval-2025 Task 10: Optimizing Context for Classification of Narrative Roles
  176. Domain Adaptation for Big Data in Agricultural Image Analysis: A Comprehensive Review
  177. On Measuring Long-Range Interactions in Graph Neural Networks
  178. Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models
  179. Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments
  180. Permutation-Free High-Order Interaction Tests
  181. Applying XAI based unsupervised knowledge discovering for Operation modes in a WWTP. A real case: AQUAVALL WWTP
  182. Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
  183. MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation
  184. Elementary Math Word Problem Generation using Large Language Models
  185. NameTag 3: A Tool and a Service for Multilingual/Multitagset NER
  186. IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systems
  187. On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization
  188. Additive decomposition of one-dimensional signals using Transformers
  189. Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting
  190. Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
  191. SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction
  192. Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling
  193. LengClaro2023: A Dataset of Administrative Texts in Spanish with Plain Language adaptations
  194. Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG
  195. Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques
  196. Over-PINNs: Enhancing Physics-Informed Neural Networks via Higher-Order Partial Derivative Overdetermination of PDEs
  197. Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness
  198. DeviceScope: An Interactive App to Detect and Localize Appliance Patterns in Electricity Consumption Time Series
  199. QualitEye: Public and Privacy-preserving Gaze Data Quality Verification
  200. Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows
  201. Proactive Assistant Dialogue Generation from Streaming Egocentric Videos
  202. A Driving Regime-Embedded Deep Learning Framework for Modeling Intra-Driver Heterogeneity in Multi-Scale Car-Following Dynamics
  203. WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
  204. Query Nearby: Offset-Adjusted Mask2Former enhances small-organ segmentation
  205. Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series
  206. Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation
  207. Variational Inference for Quantum HyperNetworks
  208. A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language
  209. NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
  210. A projection-based framework for gradient-free and parallel learning
  211. Interpretable Clustering Ensemble
  212. Information Bargaining: Bilateral Commitment in Bayesian Persuasion
  213. Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks
  214. Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
  215. BestServe: Serving Strategies with Optimal Goodput in Collocation and Disaggregation Architectures
  216. Loss Functions for Predictor-based Neural Architecture Search
  217. Stealix: Model Stealing via Prompt Evolution
  218. CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy
  219. Improved Allergy Wheal Detection for the Skin Prick Automated Test Device
  220. ChronoTailor: Harnessing Attention Guidance for Fine-Grained Video Virtual Try-On
  221. Wavelet-based Disentangled Adaptive Normalization for Non-stationary Times Series Forecasting
  222. Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025
  223. Optimized projection-free algorithms for online learning: construction and worst-case analysis
  224. Training-Free Query Optimization via LLM-Based Plan Similarity
  225. DeepFake Doctor: Diagnosing and Treating Audio-Video Fake Detection
  226. Regional, Lattice and Logical Representations of Neural Networks
  227. Fuzzy Lattice-based Description Logic
  228. HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding
  229. Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
  230. High Throughput Event Filtering: The Interpolation-based DIF Algorithm Hardware Architecture
  231. FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
  232. DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image
  233. NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
  234. Positional Encoding meets Persistent Homology on Graphs
  235. Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction
  236. Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
  237. Option Pricing Using Ensemble Learning
  238. EqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator
  239. Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
  240. EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
  241. GazeNLQ @ Ego4D Natural Language Queries Challenge 2025
  242. Robust sensor fusion against on-vehicle sensor staleness
  243. Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane
  244. AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
  245. Exploring Microstructural Dynamics in Cryptocurrency Limit Order Books: Better Inputs Matter More Than Stacking Another Hidden Layer
  246. Where Is The Ball: 3D Ball Trajectory Estimation From 2D Monocular Tracking
  247. Revealing hidden correlations from complex spatial distributions: Adjacent Correlation Analysis
  248. Mapping correlations and coherence: adjacency-based approach to data visualization and regularity discovery
  249. Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
  250. Integrating Spatiotemporal Features in LSTM for Spatially Informed COVID-19 Hospitalization Forecasting
  251. An Ontology for Representing Curriculum and Learning Material
  252. Investigating the Relationship between the Weighted Figure of Merit and Rosin's Measure
  253. Generalized Incremental Learning under Concept Drift across Evolving Data Streams
  254. Large Language Models are Good Relational Learners
  255. Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data
  256. You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Grasping
  257. Grokking Beyond the Euclidean Norm of Model Parameters
  258. Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
  259. Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces
  260. Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health
  261. RKEFino1: A Regulation Knowledge-Enhanced Large Language Model
  262. Evaluating AI-Powered Learning Assistants in Engineering Higher Education: Student Engagement, Ethical Challenges, and Policy Implications
  263. SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
  264. Voice Impression Control in Zero-Shot TTS
  265. A Unified Representation for Continuity and Discontinuity: Syntactic and Computational Motivations
  266. Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR
  267. Integer Binary-Range Alignment Neuron for Spiking Neural Networks
  268. Topology-aware Neural Flux Prediction Guided by Physics
  269. Zero-Shot Event Causality Identification via Multi-source Evidence Fuzzy Aggregation with Large Language Models
  270. Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery
  271. Contextually Guided Transformers via Low-Rank Adaptation
  272. Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
  273. Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment
  274. BAQ: Efficient Bit Allocation Quantization for Large Language Models
  275. TissUnet: Improved Extracranial Tissue and Cranium Segmentation for Children through Adulthood
  276. Emulating compact binary population synthesis simulations with uncertainty quantification and model comparison using Bayesian normalizing flows
  277. Aerial Multi-View Stereo via Adaptive Depth Range Inference and Normal Cues
  278. Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection
  279. Learning to Weight Parameters for Training Data Attribution
  280. Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones