mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 2 Oct 2024

452 papers

  1. BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge DistillationKnowledge distillation → Distillation for spiking neural networks
  2. Generative Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  3. Precision Knowledge Editing: Enhancing Safety in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  4. SeeSay: An Assistive Device for the Visually Impaired Using Retrieval Augmented GenerationRetrieval-augmented generation → Multimodal RAG
  5. SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific TasksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  6. Reasoning Elicitation in Language Models via Counterfactual FeedbackLLM reasoning → Causal reasoning in LLMs
  7. Denoising with a Joint-Embedding Predictive ArchitectureDiffusion models → Diffusion foundations and sampling
  8. Enhancing Retrieval in QA Systems with Derived Feature AssociationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  9. FlipAttack: Jailbreak LLMs via FlippingLLM safety and security → Jailbreaking
  10. Racing Thoughts: Explaining Contextualization Errors in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  11. A Watermark for Black-Box Language ModelsLLM safety and security → Watermarking generated content and models
  12. EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice RoutingDiffusion models → Diffusion foundations and sampling +1
  13. RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
  14. EMMA: Efficient Visual Alignment in Multi-Modal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-InstructSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  16. Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  17. Style Ambiguity Loss Using CLIPDiffusion models → Image generation, text-to-image and editing
  18. ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory LearningLLM reasoning → Reasoning for agents, planning and code +1
  19. Realizable Continuous-Space Shields for Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  20. Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual RetrievalMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  21. Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent DiagnosticsLLM agents and tool use → Medical and scientific domain agents
  22. CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMsLLM reasoning → Reasoning for agents, planning and code
  23. Run-time Observation Interventions Make Vision-Language-Action Models More Visually RobustVision-language-action models → Generalist VLA models and benchmarks
  24. Bi-Level Motion Imitation for Humanoid RobotsOffline RL and imitation learning from data → Real-world robot offline RL
  25. Challenges and Future Directions of Data-Centric AI AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  26. ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift RegularizationOffline RL and imitation learning from data → Offline multi-agent RL
  27. TypedThinker: Diversify Large Language Model Reasoning with Typed ThinkingLLM reasoning → Reasoning benchmarks and evaluation
  28. Discrete Copula DiffusionDiffusion models → Discrete and text diffusion
  29. CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
  30. Equality Constrained Diffusion for Direct Trajectory OptimizationDiffusion models → Diffusion and flow policies for robotics
  31. Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RLDeep reinforcement learning methods → Deep RL algorithms and representations
  32. Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte CarloLLM reasoning → Mathematical reasoning
  33. Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image WatermarkingLLM safety and security → Watermarking generated content and models
  34. OCC-MLLM-Alpha:Empowering Multi-modal Large Language Model for the Understanding of Occluded Objects with Self-Supervised Test-Time LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  35. Long-range gene expression prediction with token alignment of large language modelLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  36. Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade DevicesEfficient LLM inference and serving → KV cache optimization
  37. Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution SpaceDiffusion models → Diffusion and flow policies for robotics
  38. When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1LLM reasoning → Reasoning benchmarks and evaluation
  39. Open Human-Robot Collaboration using Decentralized Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  40. Investigating on RLHF methodologyLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  41. Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +2
  42. Dynamical-generative downscaling of climate model ensemblesDiffusion models → Flow matching, time series and science
  43. DeFine: Decision-Making with Analogical Reasoning over Factor ProfilesLLM reasoning → Test-time compute and efficient thinking
  44. ImageFolder: Autoregressive Image Generation with Folded TokensDiffusion models → Diffusion foundations and sampling
  45. Not All LLM Reasoners Are Created EqualLLM reasoning → Mathematical reasoning
  46. PreND: Enhancing Intrinsic Motivation in Reinforcement Learning through Pre-trained Network DistillationDeep reinforcement learning methods → Deep RL algorithms and representations
  47. Leopard: A Vision Language Model For Text-Rich Multi-Image TasksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  48. Conceptual Belief-Informed Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  49. VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  50. Recursive Abstractive Processing for Retrieval in Dynamic DatasetsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  51. LASeR: Learning to Adaptively Select Reward Models with Multi-Armed BanditsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  52. ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII ArtMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  53. Evaluating Robustness of Reward Models for Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  54. HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer AccelerationDiffusion models → Diffusion foundations and sampling
  55. Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck PerspectiveSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  56. COMUNI: Decomposing Common and Unique Video Signals for Diffusion-based Video GenerationDiffusion models → Video generation
  57. Interpretable Contrastive Monte Carlo Tree Search ReasoningLLM reasoning → Test-time compute and efficient thinking +1
  58. An Exploration of Self-Supervised Mutual Information Alignment for Multi-Task SettingsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  59. Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi DecodingEfficient LLM inference and serving → Fast autoregressive visual generation
  60. CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMsLLM reasoning → Causal reasoning in LLMs
  61. FactAlign: Long-form Factuality Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  62. Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalitiesLLM reasoning → Multimodal reasoning +1
  63. PHI-S: Distribution Balancing for Label-Free Multi-Teacher DistillationKnowledge distillation → General knowledge distillation methods
  64. Finding path and cycle counting formulae in graphs with Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  65. Stable Offline Value Function Learning with Bisimulation-based RepresentationsDeep reinforcement learning methods → Deep RL algorithms and representations
  66. Moral Alignment for LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  67. One-Shot Robust Imitation Learning for Long-Horizon Visuomotor Tasks from Unsegmented DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
  68. LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  69. Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter MergingMixture-of-experts → MoE large language models
  70. Computational Teaching for Driving via Multi-Task Imitation LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  71. Automated Red Teaming with GOAT: the Generative Offensive Agent TesterLLM agents and tool use → Agent threats, guardrails and governance +1
  72. KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  73. MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video GenerationDiffusion models → Audio, speech and music
  74. DynFrs: An Efficient Framework for Machine Unlearning in Random ForestLLM safety and security → Machine unlearning
  75. HRTF Estimation using a Score-based PriorDiffusion models → Audio, speech and music
  76. OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction DataLLM reasoning → Mathematical reasoning
  77. Integrative Decoding: Improve Factuality via Implicit Self-consistencyLLM reasoning → Test-time compute and efficient thinking
  78. Lines of Thought in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  79. Edge-preserving noise for diffusion modelsDiffusion models → Diffusion foundations and sampling
  80. Toward a Holistic Evaluation of Robustness in CLIP ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  81. Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  82. HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsKnowledge distillation → Knowledge distillation for LLMs
  83. PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data AugmentationLLM reasoning → Mathematical reasoning
  84. Discrete Diffusion Schr"odinger Bridge Matching for Graph TransformationDiffusion models → Diffusion foundations and sampling
  85. A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial ContextsEfficient LLM inference and serving → KV cache optimization
  86. Agent-Driven Large Language Models for Mandarin Lyric GenerationLLM agents and tool use → Multimodal and embodied agents
  87. The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  88. Scalable Reinforcement Learning-based Neural Architecture SearchDeep reinforcement learning methods → Deep RL algorithms and representations
  89. Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging TasksLLM reasoning → Knowledge- and tool-augmented reasoning
  90. The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  91. AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model AlignmentMultimodal LLMs / vision-language models → Agricultural vision-language models
  92. Harnessing the Latent Diffusion Model for Training-Free Image Style TransferDiffusion models → Image generation, text-to-image and editing
  93. Sampling from Energy-based Policies using DiffusionDeep reinforcement learning methods → RL with diffusion and flow models
  94. FanCric : Multi-Agentic Framework for Crafting Fantasy 11 Cricket TeamsLLM agents and tool use → Reinforcement learning for LLM agents
  95. Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response GenerationLLM reasoning → Audio-language model reasoning
  96. Endless Jailbreaks with Bijection LearningLLM safety and security → Jailbreaking
  97. Robust Imitation Learning for Mobile Manipulator Focusing on Task-Related Viewpoints and RegionsOffline RL and imitation learning from data → Robot manipulation imitation learning
  98. Sparse Autoencoders Reveal Temporal Difference Learning in Large Language ModelsMechanistic interpretability → SAE features and their applications
  99. Deep Unlearn: Benchmarking Machine Unlearning for Image ClassificationLLM safety and security → Machine unlearning
  100. CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot InteractionOffline RL and imitation learning from data → Language-conditioned policies and VLAs
All 452
  1. Backdooring Vision-Language Models with Out-Of-Distribution DataMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  2. Improving Fine-Grained Control via Aggregation of Multiple Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  3. OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded ObjectsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. HelpSteer2-Preference: Complementing Ratings with PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  5. AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended ResponsesLLM reasoning → Reasoning benchmarks and evaluation
  6. Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space DivergencesDiffusion models → Flow matching, time series and science
  7. RGD: Multi-LLM Based Agent Debugger via Refinement and Generation GuidanceLLM agents and tool use → Software engineering coding agents
  8. Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints SatisfactionDeep reinforcement learning methods → Safe and constrained RL
  9. Stochastic Gradient Descent with Adaptive DataDeep reinforcement learning methods → RL theory and sample complexity
  10. Towards Inference-time Category-wise Safety Steering for Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  11. Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual RobustnessRetrieval-augmented generation → Generation and context integration
  12. Text2PDE: Latent Diffusion Models for Accessible Physics SimulationDiffusion models → Flow matching, time series and science
  13. SSL-NBV: A Self-Supervised-Learning-Based Next-Best-View algorithm for Efficient 3D Plant Reconstruction by a Robot
  14. ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models
  15. Deep Knowledge Tracing for Personalized Adaptive Learning at Historically Black Colleges and Universities
  16. Chain-Oriented Objective Logic with Neural Network Feedback Control and Cascade Filtering for Dynamic Multi-DSL Regulation
  17. On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants
  18. Explaining an image classifier with a generative model conditioned by uncertainty
  19. A Federated Learning Platform as a Service for Advancing Stroke Management in European Clinical Centers
  20. Stars, Stripes, and Silicon: Unravelling the ChatGPT's All-American, Monochrome, Cis-centric Bias
  21. Self-Supervised Pre-Training with Joint-Embedding Predictive Architecture Boosts ECG Classification Performance
  22. Associative memory and dead neurons
  23. MyData: A Comprehensive Database of Mycetoma Tissue Microscopic Images for Histopathological Analysis
  24. Segment as You Wish -- Free-Form Language-Based Segmentation for Medical Images
  25. Incorporating Metabolic Information into LLMs for Anomaly Detection in Clinical Time-Series
  26. GCM-Net: Graph-enhanced Cross-Modal Infusion with a Metaheuristic-Driven Network for Video Sentiment and Emotion Analysis
  27. DyMix: Dynamic Frequency Mixup Scheduler based Unsupervised Domain Adaptation for Enhancing Alzheimer's Disease Identification
  28. GeoLife+: Large-Scale Simulated Trajectory Datasets Calibrated to the GeoLife Dataset
  29. A Real Benchmark Swell Noise Dataset for Performing Seismic Data Denoising via Deep Learning
  30. Learning to learn ecosystems from limited data -- a meta-learning approach
  31. Distilling Analysis from Generative Models for Investment Decisions
  32. MARS: A neurosymbolic approach for interpretable drug discovery
  33. Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language
  34. A Two-Stage Proactive Dialogue Generator for Efficient Clinical Information Collection Using Large Language Model
  35. Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
  36. FutureFill: Fast Generation from Convolutional Sequence Models
  37. Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression
  38. Words that Represent Peace
  39. Getting in the Door: Streamlining Intake in Civil Legal Services with Large Language Models
  40. Taxonomy Tree Generation from Citation Graph
  41. On the SAGA algorithm with decreasing step
  42. Towards a Deeper Understanding of Transformer for Residential Non-intrusive Load Monitoring
  43. The Smart Buildings Control Suite: A Diverse Open Source Benchmark to Evaluate and Scale HVAC Control Policies for Sustainability
  44. Efficient Streaming LLM for Speech Recognition
  45. The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
  46. Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization
  47. MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis
  48. Symmetry-Robust 3D Orientation Estimation
  49. Tracking objects that change in appearance with phase synchrony
  50. The Impact of Generative AI on Collaborative Open-Source Software Development: Evidence from GitHub Copilot
  51. HyperBrain: Anomaly Detection for Temporal Hypergraph Brain Networks
  52. Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations
  53. Multi-Omic and Quantum Machine Learning Integration for Lung Subtypes Classification
  54. FARM: Enhancing Molecular Representations with Functional Group Awareness
  55. MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameters
  56. Deep Generative Modeling for Identification of Noisy, Non-Stationary Dynamical Systems
  57. Posterior sampling via Langevin dynamics based on generative priors
  58. Kolmogorov-Arnold Network Autoencoders
  59. Price-guided user attention in large-scale E-commerce group recommendation
  60. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
  61. A Practical Approach to Underwater Depth and Surface Normals Estimation
  62. MMFNet: Multi-Scale Frequency Masking Neural Network for Multivariate Time Series Forecasting
  63. Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition
  64. Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
  65. DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation
  66. TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models
  67. PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations
  68. Emo3D: Metric and Benchmarking Dataset for 3D Facial Expression Generation from Emotion Description
  69. FeelAnyForce: Estimating Contact Force Feedback from Tactile Sensation for Vision-Based Tactile Sensors
  70. Impact of White-Box Adversarial Attacks on Convolutional Neural Networks
  71. EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning
  72. Tuning Frequency Bias of State Space Models
  73. Model Comparisons: XNet Outperforms KAN
  74. Neural Eulerian Scene Flow Fields
  75. Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions
  76. A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
  77. FLAG: Financial Long Document Classification via AMR-based GNN
  78. DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning
  79. Review Non-convex Optimization Method for Machine Learning
  80. Adaptively Private Next-Token Prediction of Large Language Models
  81. Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images
  82. MONICA: Benchmarking on Long-tailed Medical Image Classification
  83. An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration
  84. FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness
  85. Normalizing Flow-Based Metric for Image Generation
  86. TerrAInav Sim: An Open-Source Simulation of UAV Aerial Imaging from Satellite Data
  87. Deep Learning Alternatives of the Kolmogorov Superposition Theorem
  88. UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription
  89. Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT
  90. Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Tasks
  91. Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers
  92. LLM+KG@VLDB'24 Workshop Summary
  93. Which Algorithms Have Tight Generalization Bounds?
  94. Enhancing Screen Time Identification in Children with a Multi-View Vision Language Model and Screen Time Tracker
  95. LS-HAR: Language Supervised Human Action Recognition with Salient Fusion, Construction Sites as a Use-Case
  96. Scale-Invariant Learning-to-Rank
  97. Quantum-data-driven dynamical transition in quantum learning
  98. Generate then Refine: Data Augmentation for Zero-shot Intent Detection
  99. Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
  100. SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics
  101. LFQA-E: Carefully Benchmarking Long-form QA Evaluation
  102. Debiased Orthogonal Boundary-Driven Efficient Noise Mitigation
  103. TAEGAN: Generating Synthetic Tabular Data For Data Augmentation
  104. LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition
  105. Deep learning assisted high resolution microscopy image processing for phase segmentation in functional composite materials
  106. Risk Alignment in Agentic AI Systems
  107. MARPLE: A Benchmark for Long-Horizon Inference
  108. NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
  109. Provably Accurate Shapley Value Estimation via Leverage Score Sampling
  110. A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
  111. Is uniform expressivity too restrictive? Towards efficient expressivity of graph neural networks
  112. The potential of LLM-generated reports in DevSecOps
  113. Conformal Prediction Sets Can Cause Disparate Impact
  114. Auction-Based Regulation for Artificial Intelligence
  115. PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
  116. Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement
  117. House of Cards: Massive Weights in LLMs
  118. Simplifying complex machine learning by linearly separable network embedding spaces
  119. Dynamic Portfolio Rebalancing: A Hybrid new Model Using GNNs and Pathfinding for Cost Efficiency
  120. FredNormer: Frequency Domain Normalization for Non-stationary Time Series Forecasting
  121. Enhancing End Stage Renal Disease Outcome Prediction: A Multi-Sourced Data-Driven Approach
  122. Learning the Optimal Path and DNN Partition for Collaborative Edge Inference
  123. Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking
  124. EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis
  125. On the expressiveness and spectral bias of KANs
  126. PROXI: Challenging the GNNs for Link Prediction
  127. FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Clothing Images
  128. Efficient 1-bit tensor approximations
  129. Windowed MAPF with Completeness Guarantees
  130. Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models
  131. Loki: An Open-Source Tool for Fact Verification
  132. Thermodynamic Bayesian Inference
  133. DreamGarden: A Designer Assistant for Growing Games from a Single Prompt
  134. Learning To Solve Differential Equation Constrained Optimization Problems
  135. OmniGenBench: Automating Large-scale in-silico Benchmarking for Genomic Foundation Models
  136. On metric choice in dimension reduction for Fr'echet regression
  137. Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
  138. TopER: Topological Embeddings in Graph Representation Learning
  139. Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
  140. Bayesian Binary Search
  141. Explainable Earth Surface Forecasting under Extreme Events
  142. Quantifying Generalization Complexity for Large Language Models
  143. SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
  144. Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
  145. SegHeD: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints
  146. Integrating Protein Sequence and Expression Level to Analysis Molecular Characterization of Breast Cancer Subtypes
  147. TorchSISSO: A PyTorch-Based Implementation of the Sure Independence Screening and Sparsifying Operator for Efficient and Interpretable Model Discovery
  148. Leray-Schauder Mappings for Operator Learning
  149. Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark
  150. ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation
  151. Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing
  152. Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting
  153. OmniSR: Shadow Removal under Direct and Indirect Lighting
  154. Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training
  155. Examining the Role of Relationship Alignment in Large Language Models
  156. Sable: a Performant, Efficient and Scalable Sequence Model for MARL
  157. COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation
  158. Enhancing Adversarial Robustness through Multi-Objective Representation Learning
  159. From Prohibition to Adoption: How Hong Kong Universities Are Navigating ChatGPT in Academic Workflows
  160. U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models
  161. Uncertainty Quantification with Bayesian Higher Order ReLU KANs
  162. Positional Attention: Expressivity and Learnability of Algorithmic Computation
  163. VinePPO: Refining Credit Assignment in RL Training of LLMs
  164. Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking
  165. Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia
  166. Linguistic traces of stochastic empathy in language models
  167. Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
  168. Sparse Covariance Neural Networks
  169. Towards a vision foundation model for comprehensive assessment of Cardiac MRI
  170. Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering
  171. Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening
  172. Scalable and Consistent Graph Neural Networks for Distributed Mesh-based Data-driven Modeling
  173. Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians
  174. Reevaluating Meta-Learning Optimization Algorithms Through Contextual Self-Modulation
  175. Releasing the Parameter Latency of Neural Representation for High-Efficiency Video Compression
  176. Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
  177. shapiq: Shapley Interactions for Machine Learning
  178. DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment
  179. 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detection
  180. A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT
  181. Data Extrapolation for Text-to-image Generation on Small Datasets
  182. On The Adaptation of Unlimiformer for Decoder-Only Transformers
  183. Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
  184. A Thematic Framework for Analyzing Large-scale Self-reported Social Media Data on Opioid Use Disorder Treatment Using Buprenorphine Product
  185. Stochasticity in Motion: An Information-Theoretic Approach to Trajectory Prediction
  186. Intent Detection in the Age of LLMs
  187. Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
  188. SGBA: Semantic Gaussian Mixture Model-Based LiDAR Bundle Adjustment
  189. On Using Certified Training towards Empirical Robustness
  190. Saliency-Guided DETR for Moment Retrieval and Highlight Detection
  191. Gaussian Splatting in Mirrors: Reflection-Aware Rendering via Virtual Camera Optimization
  192. DRUPI: Dataset Reduction Using Privileged Information
  193. SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction
  194. ENTP: Encoder-only Next Token Prediction
  195. Towards Model Discovery Using Domain Decomposition and PINNs
  196. Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendation
  197. SAFE: Semantic Adaptive Feature Extraction with Rate Control for 6G Wireless Communications
  198. Imaging foundation model for universal enhancement of non-ideal measurement CT
  199. Iterated Local Search with Linkage Learning
  200. Learning-Augmented Robust Algorithmic Recourse
  201. Spoken Grammar Assessment Using LLM
  202. Coordinate-Based Neural Representation Enabling Zero-Shot Learning for 3D Multiparametric Quantitative MRI
  203. Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games
  204. Adversarial Robustness of AI-Generated Image Detectors in the Real World
  205. PASS:Test-Time Prompting to Adapt Styles and Semantic Shapes in Medical Image Segmentation
  206. Truncated Kernel Stochastic Gradient Descent on Spheres
  207. Bayes' Power for Explaining In-Context Learning Generalizations
  208. ACE: A LLM-based Negotiation Coaching System
  209. MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills
  210. In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks
  211. Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension
  212. Multi-Scale Fusion for Object Representation
  213. Attention layers provably solve single-location regression
  214. EUFCC-CIR: a Composed Image Retrieval Dataset for GLAM Collections
  215. GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians
  216. TiVaT: A Transformer with a Single Unified Mechanism for Capturing Asynchronous Dependencies in Multivariate Time Series Forecasting
  217. Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning
  218. MiraGe: Editable 2D Images using Gaussian Splatting
  219. InfiniPot: Infinite Context Processing on Memory-Constrained LLMs
  220. UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction
  221. Bounds on Lp errors in density ratio estimation via f-divergence loss functions
  222. InstaTrans: An Instruction-Aware Translation Framework for Non-English Instruction Datasets
  223. Disentangling Latent Shifts of In-Context Learning with Weak Supervision
  224. Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion
  225. Quo Vadis RankList-based System in Face Recognition?
  226. DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models
  227. Extending Context Window of Large Language Models from a Distributional Perspective
  228. Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas
  229. Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks
  230. One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
  231. SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
  232. Introducing Flexible Monotone Multiple Choice Item Response Theory Models and Bit Scales
  233. Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks
  234. SinkSAM-Net: Knowledge-Driven Self-Supervised Sinkhole Segmentation Using Topographic Priors and Segment Anything Model
  235. Peeling Back the Layers: An In-Depth Evaluation of Encoder Architectures in Neural News Recommenders
  236. TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
  237. Flow Matching for Accelerated Simulation of Atomic Transport in Crystalline Materials
  238. Selective Aggregation for Low-Rank Adaptation in Federated Learning
  239. From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge
  240. Verbalized Graph Representation Learning: A Fully Interpretable Graph Model Based on Large Language Models Throughout the Entire Process
  241. Ensembles provably learn equivariance through data augmentation
  242. Analyzing Byte-Pair Encoding on Monophonic and Polyphonic Symbolic Music: A Focus on Musical Phrase Segmentation
  243. Geometric Signatures of Compositionality Across a Language Model's Lifetime
  244. SurgPointTransformer: Vertebrae Shape Completion with RGB-D Data
  245. Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
  246. Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
  247. Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
  248. Adaptive teachers for amortized samplers
  249. Approximation by Steklov Neural Network Operators
  250. EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settings
  251. Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation
  252. Improving Fuzzy Rule Classifier with Brain Storm Optimization and Rule Modification
  253. CSIM: A Copula-based similarity index sensitive to local changes for Image quality assessment
  254. On the Convergence of FedProx with Extrapolation and Inexact Prox
  255. SHAP-CAT: A interpretable multi-modal framework enhancing WSI classification via virtual staining and shapley-value-based multimodal fusion
  256. On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
  257. Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection
  258. Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering
  259. CrowdCounter: A benchmark type-specific multi-target counterspeech dataset
  260. Overpredictive Signal Analytics in Federated Learning: Algorithms and Analysis
  261. Easy Come, Easy Go? Examining the Perceptions and Learning Effects of LLM-based Chatbot in the Context of Search-as-Learning
  262. Toward Zero-Shot Learning for Visual Dehazing of Urological Surgical Robots
  263. Gaussian kernel expansion with basis functions uniformly bounded in L∞
  264. Signal Adversarial Examples Generation for Signal Detection Network via White-Box Attack
  265. Causal Inference Tools for a Better Evaluation of Machine Learning
  266. Quantifying Cancer Likeness: A Statistical Approach for Pathological Image Diagnosis
  267. FLAME: Adaptive and Reactive Concept Drift Mitigation for Federated Learning Deployments
  268. PairDistill: Pairwise Relevance Distillation for Dense Retrieval
  269. Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
  270. Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems
  271. Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
  272. Theoretical Lower Bounds for the Oven Scheduling Problem
  273. Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
  274. Anti-biofouling Lensless Camera System with Deep Learning based Image Reconstruction
  275. PCQPR: Proactive Conversational Question Planning with Reflection
  276. High-quality Animatable Eyelid Shapes from Lightweight Captures
  277. FlashMask: Efficient and Rich Mask Extension of FlashAttention
  278. Assisted Data Annotation for Business Process Information Extraction from Textual Documents
  279. Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
  280. Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling
  281. Life, uh, Finds a Way: Hyperadaptability by Behavioral Search
  282. Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy
  283. Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
  284. Response Estimation and System Identification of Dynamical Systems via Physics-Informed Neural Networks
  285. PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems
  286. VectorGraphNET: Graph Attention Networks for Accurate Segmentation of Complex Technical Drawings
  287. Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
  288. Skill Path: Unveiling Language Skills from Circuit Graphs
  289. Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting
  290. Fair Class-Incremental Learning using Sample Weighting
  291. Forte : Finding Outliers with Representation Typicality Estimation
  292. Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps
  293. Fast Summation of Radial Kernels via QMC Slicing
  294. Getting Free Bits Back from Rotational Symmetries in LLMs
  295. How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?
  296. Revisiting Hierarchical Text Classification: Inference and Metrics
  297. Deep learning for action spotting in association football videos
  298. Speculative Coreset Selection for Task-Specific Fine-tuning
  299. LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion
  300. SurgeoNet: Realtime 3D Pose Estimation of Articulated Surgical Instruments from Stereo Images using a Synthetically-trained Network
  301. Towards a Law of Iterated Expectations for Heuristic Estimators
  302. Mitigating Copy Bias in In-Context Learning through Neuron Pruning
  303. Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
  304. Deep Kernel Posterior Learning under Infinite Variance Prior Weights
  305. Uncertainty-aware Human Mobility Modeling and Anomaly Detection
  306. "No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
  307. Panopticus: Omnidirectional 3D Object Detection on Resource-constrained Edge Devices
  308. Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Unveiling AI's Potential Through Tools, Techniques, and Applications
  309. Transformers Handle Endogeneity in In-Context Linear Regression
  310. Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learning
  311. Resource-efficient equivariant quantum convolutional neural networks
  312. Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample
  313. Dual Approximation Policy Optimization
  314. Automatic deductive coding in discourse analysis: an application of large language models in learning analytics
  315. Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters
  316. ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
  317. See Me, Believe Me: Causality, Intersectionality, and Interventions Improving the Appearance of Patients
  318. Towards Native Generative Model for 3D Head Avatar
  319. Perceptual Piercing: Human Visual Cue-based Object Detection in Low Visibility Conditions
  320. Statistical Taylor Expansion: A New and Path-Independent Method for Uncertainty Analysis
  321. Induced Covariance for Causal Discovery in Linear Sparse Structures
  322. Effective Tuning Strategies for Generalist Robot Manipulation Policies
  323. An uncertainty-aware Digital Shadow for underground multimodal CO2 storage monitoring
  324. RS-FME-SwinT: A Novel Feature Map Enhancement Framework Integrating Customized SwinT with Residual and Spatial CNN for Monkeypox Diagnosis
  325. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
  326. A versatile machine learning workflow for high-throughput analysis of supported metal catalyst particles
  327. Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model
  328. Debiasing Federated Learning with Correlated Client Participation
  329. StringLLM: Understanding the String Processing Capability of Large Language Models
  330. AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction
  331. Were RNNs All We Needed?
  332. Expected Diverse Utility (EDU): Diverse Bayesian Optimization of Expensive Computer Simulators
  333. [Re] Network Deconvolution
  334. Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs
  335. Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate
  336. Formula-Driven Data Augmentation and Partial Retinal Layer Copying for Retinal Layer Segmentation
  337. FastLexRank: Efficient Lexical Ranking for Structuring Social Media Posts
  338. UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark
  339. Generative Diffusion-based Contract Design for Efficient AI Twins Migration in Vehicular Embodied AI Networks
  340. Unifying the Scope of Bridging Anaphora Types in English: Bridging Annotations in ARRAU and GUM
  341. GADFA: Generator-Assisted Decision-Focused Approach for Opinion Expressing Timing Identification
  342. Document Classification using File Names
  343. Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
  344. GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network
  345. A Deep Learning Approach for Imbalanced Tabular Data in Advertiser Prospecting: A Case of Direct Mail Prospecting
  346. Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting
  347. Recovering Manifold Structure Using Ollivier-Ricci Curvature
  348. Automatic Image Unfolding and Stitching Framework for Esophageal Lining Video Based on Density-Weighted Feature Matching
  349. ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups
  350. Uncertainty-Guided Enhancement on Driving Perception System via Foundation Models
  351. Evaluating Deduplication Techniques for Economic Research Paper Titles with a Focus on Semantic Similarity using NLP and LLMs
  352. Explain Like I'm Five: Using LLMs to Improve PDE Surrogate Models with Text