mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 23 May 2024

490 papers

  1. Measurement Embedded Schr"odinger Bridge for Inverse ProblemsDiffusion models → Diffusion foundations and sampling
  2. Pre-Trained Vision-Language Models as Partial AnnotatorsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  3. Ferrari: Federated Feature Unlearning via Optimizing Feature SensitivityLLM safety and security → Federated unlearning and poisoning
  4. Efficient Mitigation of Bus Bunching through Setter-Based Curriculum LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  5. Reinforcing Language Agents via Policy Optimization with Action DecompositionLLM agents and tool use → Reinforcement learning for LLM agents
  6. Dissociation of Faithful and Unfaithful Reasoning in LLMsLLM reasoning → Prompting and chain-of-thought reasoning
  7. MuDreamer: Learning Predictive World Models without ReconstructionWorld models → Latent dynamics models and model-based RL
  8. Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of GeneralizationLLM reasoning → Reasoning benchmarks and evaluation
  9. Optimizing example selection for retrieval-augmented machine translation with translation memoriesRetrieval-augmented generation → Generation and context integration
  10. Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary PreferencesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  11. Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative ReasoningLLM reasoning → Spatial and embodied reasoning
  12. Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM TrainingMixture-of-experts → Efficient MoE training and inference systems
  13. Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPsDeep reinforcement learning methods → RL theory and sample complexity
  14. CEEBERT: Cross-Domain Inference in Early Exit BERTEfficient LLM inference and serving → Early exit and edge inference
  15. Amortized nonmyopic active search via deep imitation learningOffline RL and imitation learning from data → Imitation learning methods
  16. AdjointDEIS: Efficient Gradients for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  17. Agentic Skill DiscoveryLLM reasoning → Spatial and embodied reasoning +1
  18. CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry RefinerDiffusion models → 3D, point cloud and scene generation
  19. A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  20. Efficiently Training Deep-Learning Parametric Policies using Lagrangian DualityDeep reinforcement learning methods → RL theory and sample complexity
  21. SFDDM: Single-fold Distillation for Diffusion modelsDiffusion models → Diffusion foundations and sampling
  22. Interpretable and Editable Programmatic Tree Policies for Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  23. MallowsPO: Fine-Tune Your LLM with Preference DispersionsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  24. Improved Distribution Matching Distillation for Fast Image SynthesisDiffusion models → Diffusion foundations and sampling
  25. Video Diffusion Models are Training-free Motion Interpreter and ControllerDiffusion models → Video generation
  26. Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  27. Mamba-R: Vision Mamba ALSO Needs RegistersState-space sequence models (S4, Mamba) → Vision Mamba backbones
  28. Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image VariationsDiffusion models → Image generation, text-to-image and editing
  29. TerDiT: Ternary Diffusion Models with TransformersDiffusion models → Diffusion foundations and sampling
  30. From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by StepLLM reasoning → Prompting and chain-of-thought reasoning
  31. Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion TransformerDiffusion models → 3D, point cloud and scene generation
  32. HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsRetrieval-augmented generation → Generation and context integration
  33. Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  34. PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion TeacherDiffusion models → Diffusion foundations and sampling
  35. Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image GenerationDiffusion models → Medical imaging and segmentation
  36. Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood DiscrepancyDiffusion models → Robustness, privacy and adversarial aspects +1
  37. Recurrent Early Exits for Federated Learning with Heterogeneous ClientsKnowledge distillation → Federated, robust and private distillation
  38. EditWorld: Simulating World Dynamics for Instruction-Following Image EditingDiffusion models → Image generation, text-to-image and editing
  39. Metric Flow Matching for Smooth Interpolations on the Data ManifoldDiffusion models → Flow matching, time series and science
  40. Physics-informed Score-based Diffusion Model for Limited-angle Reconstruction of Cardiac Computed TomographyDiffusion models → Medical imaging and segmentation
  41. Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human InputLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  42. WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  43. FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language ModelsLLM agents and tool use → Financial trading and forecasting agents
  44. Axioms for AI Alignment from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  45. AGILE: A Novel Reinforcement Learning Framework of LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  46. On the Approximation and Convergence of Distributional Policy Gradient Algorithms for Risk-Sensitive Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  47. Exploring Prosocial Irrationality for LLM Agents: A Social Cognition ViewLLM agents and tool use → Social simulation and multi-agent debate
  48. SimPO: Simple Preference Optimization with a Reference-Free RewardLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  49. Distilling Vision-Language Pretraining for Efficient Cross-Modal RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  50. Towards Cross-modal Backward-compatible Representation Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  51. RectifID: Personalizing Rectified Flow with Anchored Classifier GuidanceDiffusion models → Image generation, text-to-image and editing
  52. Fisher Flow Matching for Generative Modeling over Discrete DataDiffusion models → Flow matching, time series and science
  53. Multi-turn Reinforcement Learning from Preference Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  54. DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +2
  55. Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of ExperiencesDeep reinforcement learning methods → Deep RL algorithms and representations
  56. Calibrated Self-Rewarding Vision Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  57. Explaining Multi-modal Large Language Models by Analyzing their Vision PerceptionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  58. Watermarking Low-entropy Generation for Large Language Models: An Unbiased and Low-risk MethodLLM safety and security → Watermarking generated content and models
  59. Neuroexplicit Diffusion Models for Inpainting of Optical Flow FieldsDiffusion models → 3D, point cloud and scene generation
  60. Visual Echoes: A Simple Unified Transformer for Audio-Visual GenerationDiffusion models → Audio, speech and music
  61. Representation Noising: A Defence Mechanism Against Harmful FinetuningLLM safety and security → Safety alignment, refusal and guardrails
  62. SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet KnowledgeMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  63. Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-ContrastMixture-of-experts → MoE theory and gating functions
  64. Impact of Non-Standard Unicode Characters on Security and Comprehension in Large Language ModelsLLM safety and security → Jailbreaking
  65. LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  66. MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street ScenesWorld models → World models for autonomous driving
  67. Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic SegmentationEfficient LLM inference and serving → Token pruning and merging for ViTs
  68. TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent EditingDiffusion models → 3D, point cloud and scene generation
  69. Adversarial Schr"odinger Bridge MatchingDiffusion models → Diffusion foundations and sampling
  70. LARS-VSA: A Vector Symbolic Architecture For Learning with Abstract RulesLLM reasoning → Multimodal reasoning
  71. RaFe: Ranking Feedback Improves Query Rewriting for RAGRetrieval-augmented generation → Generation and context integration
  72. PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers InferenceDiffusion models → Diffusion foundations and sampling
  73. Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient TransformationLLM safety and security → Graph unlearning
  74. Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing FlowsDiffusion models → Flow matching, time series and science
  75. Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  76. Can Large Language Models Create New Knowledge for Spatial Reasoning Tasks?LLM reasoning → Spatial and embodied reasoning
  77. State-Constrained Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  78. Learning Constrained Markov Decision Processes With Non-stationary Rewards and ConstraintsDeep reinforcement learning methods → RL theory and sample complexity
  79. EdgeShard: Efficient LLM Inference via Collaborative Edge ComputingEfficient LLM inference and serving → Early exit and edge inference
  80. MiniCache: KV Cache Compression in Depth Dimension for Large Language ModelsEfficient LLM inference and serving → KV cache optimization
  81. JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis ModelsLLM reasoning → Mathematical reasoning +1
  82. Doubly-Dynamic ISAC Precoding for Vehicular Networks: A Constrained Deep Reinforcement Learning (CDRL) ApproachDeep reinforcement learning methods → RL for energy, networks and operations
  83. MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space ModelsState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  84. DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic DataSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  85. Towards Efficient LLM Grounding for Embodied Multi-Agent CollaborationLLM reasoning → Reasoning for agents, planning and code +1
  86. AdaGMLP: AdaBoosting GNN-to-MLP Knowledge DistillationKnowledge distillation → Graph neural network distillation
  87. Bracket Diffusion: HDR Image Generation by Consistent LDR DenoisingDiffusion models → Inverse problems and image restoration
  88. Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer ModelsMixture-of-experts → Expert routing strategies
  89. Deep Reinforcement Learning for 5*5 Multiplayer GoDeep reinforcement learning methods → RL for games and combinatorial optimization
  90. Graph Sparsification via Mixture of GraphsMixture-of-experts → MoE for time series and graphs
  91. ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token IdentificationEfficient LLM inference and serving → KV cache quantization
  92. Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errorsDiffusion models → Diffusion foundations and sampling
  93. Tell me why: Training preferences-based RL with human preferences and step-level explanationsDeep reinforcement learning methods → RL training of language and agent models
  94. Variational Delayed Policy OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  95. DiM: Diffusion Mamba for Efficient High-Resolution Image SynthesisDiffusion models → Medical imaging and segmentation +1
  96. A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change PointsDeep reinforcement learning methods → Deep RL algorithms and representations
  97. From Text to Pixel: Advancing Long-Context Understanding in MLLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  98. Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic DataSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  99. Agent Planning with World Knowledge ModelWorld models → World models for language agents +1
  100. FreeTuner: Any Subject in Any Style with Training-free DiffusionDiffusion models → Image generation, text-to-image and editing
All 490
  1. Adaptive Teaching in Heterogeneous Agents: Balancing Surprise in Sparse Reward ScenariosOffline RL and imitation learning from data → Robot learning from demonstration
  2. Efficient Universal Goal Hijacking with Semantics-guided Prompt OrganizationLLM safety and security → Prompt injection and agent security
  3. Deterministic Policies for Constrained Reinforcement Learning in Polynomial TimeDeep reinforcement learning methods → RL theory and sample complexity
  4. Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  5. Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with TypographyLLM reasoning → Chain-of-thought reasoning for driving
  6. Unveiling the Tapestry of Consistency in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  7. RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic ReportsMultimodal LLMs / vision-language models → Medical vision-language models
  8. Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All PersonalizationDiffusion models → Image generation, text-to-image and editing
  9. Statistical Advantages of Perturbing Cosine Router in Mixture of ExpertsMixture-of-experts → Expert routing strategies
  10. AlignGPT: Multi-modal Large Language Models with Adaptive Alignment CapabilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. Transformers for Image-Goal NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  12. The Disappearance of Timestep Embedding in Modern Time-Dependent Neural NetworksDiffusion models → Diffusion foundations and sampling
  13. ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks +2
  14. Mixture of Experts Meets Prompt-Based Continual LearningMixture-of-experts → Mixture of LoRA experts
  15. Offline Reinforcement Learning from Datasets with Structured Non-StationarityOffline RL and imitation learning from data → Offline RL algorithms
  16. Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model InferenceEfficient LLM inference and serving → Speculative decoding
  17. Online Self-Preferring Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  18. Enhancing Image Layout Control with Loss-Guided Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  19. A Survey on Vision-Language-Action Models for Embodied AIVision-language-action models → Generalist VLA models and benchmarks
  20. Exclusively Penalized Q-learning for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  21. A finite time analysis of distributed Q-learningDeep reinforcement learning methods → RL theory and sample complexity
  22. T2 of Thoughts: Temperature Tree Elicits Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  23. PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  24. The Dual Imperative: Innovation and Regulation in the AI Era
  25. Preliminary Study of the Impact of AI-Based Interventions on Health and Behavioral Outcomes in Maternal Health Programs
  26. In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models
  27. Social AI and The Equation of Wittgenstein's Language User With Calvino's Literature Machine
  28. Deep Convolutional Neural Networks Meet Variational Shape Compactness Priors for Image Segmentation
  29. Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery
  30. GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time Rendering
  31. Advancements in Feature Extraction Recognition of Medical Imaging Systems Through Deep Learning Technique
  32. Exploration of Multi-Scale Image Fusion Systems in Intelligent Medical Image Analysis
  33. Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning
  34. CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning
  35. Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
  36. EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records
  37. Large Language Models' Detection of Political Orientation in Newspapers
  38. PTA: Enhancing Multimodal Sentiment Analysis through Pipelined Prediction and Translation-based Alignment
  39. Exploration of Attention Mechanism-Enhanced Deep Learning Models in the Mining of Medical Textual Data
  40. Small Language Models for Application Interactions: A Case Study
  41. Feature Fusion for Improved Classification: Combining Dempster-Shafer Theory and Multiple CNN Architectures
  42. An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals
  43. Enhancing Trust and Security in the Vehicular Metaverse: A Reputation-Based Mechanism for Participants with Moral Hazard
  44. Rotations of G"odel algebras with modal operators
  45. Sports center customer segmentation: a case study
  46. Distributed Continual Learning
  47. Information Fusion in Smart Agriculture: Machine Learning Applications and Future Research Directions
  48. Data Valuation by Fusing Global and Local Statistical Information
  49. Is Thompson Sampling Susceptible to Algorithmic Collusion?
  50. EMR-Merging: Tuning-Free High-Performance Model Merging
  51. Investigation of Customized Medical Decision Algorithms Utilizing Graph Neural Networks
  52. Integrating Medical Imaging and Clinical Reports Using Multimodal Deep Learning for Advanced Disease Analysis
  53. Blood Glucose Control Via Pre-trained Counterfactual Invertible Neural Networks
  54. How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator
  55. Efficient Point Transformer with Dynamic Token Aggregating for LiDAR Point Cloud Processing
  56. 3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation
  57. DuanzAI: Slang-Enhanced LLM with Prompt for Humor Understanding
  58. Rethinking the Elementary Function Fusion for Single-Image Dehazing
  59. Is Algorithmic Stability Testable? A Unified Framework under Computational Constraints
  60. Conformal Classification with Equalized Coverage for Adaptively Selected Groups
  61. Certified Inventory Control of Critical Resources
  62. The Rarity of Musical Audio Signals Within the Space of Possible Audio Generation
  63. Magnetic Resonance Image Processing Transformer for General Accelerated Image Reconstruction
  64. Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding
  65. Music Genre Classification: Training an AI model
  66. ULTRA-MC: A Unified Approach to Learning Mixtures of Markov Chains via Hitting Times
  67. Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget
  68. Efficient Certificates of Anti-Concentration Beyond Gaussians
  69. Distributed Harmonization: Federated Clustered Batch Effect Adjustment and Generalization
  70. A Survey of Distributed Learning in Cloud, Mobile, and Edge Settings
  71. Eliciting Informative Text Evaluations with Large Language Models
  72. 4+3 Phases of Compute-Optimal Neural Scaling Laws
  73. Temporal Stamp Classifier: Classifying Short Sequences of Astronomical Alerts
  74. Promoting Constructive Deliberation: Reframing for Receptiveness
  75. A classification model based on a population of hypergraphs
  76. Model-Agnostic Utility-Preserving Biometric Information Anonymization
  77. Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks
  78. ElastoGen: 4D Generative Elastodynamics
  79. CCBNet: Confidential Collaborative Bayesian Networks Inference
  80. Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
  81. Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification
  82. Input-driven circuit reconfiguration in critical recurrent neural networks
  83. Fractured Glass, Failing Cameras: Simulating Physics-Based Adversarial Samples for Autonomous Driving Systems
  84. Aya 23: Open Weight Releases to Further Multilingual Progress
  85. AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings
  86. OAC: Output-adaptive Calibration for Accurate Post-training Quantization
  87. What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
  88. Fast Inference with Kronecker-Sparse Matrices
  89. Extracting Prompts by Inverting LLM Outputs
  90. Parameter-free Clipped Gradient Descent Meets Polyak
  91. RE-Adapt: Reverse Engineered Adaptation of Large Language Models
  92. A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations
  93. Private Regression via Data-Dependent Sufficient Statistic Perturbation
  94. Lower Bound on the Greedy Approximation Ratio for Adaptive Submodular Cover
  95. Linking In-context Learning in Transformers to Human Episodic Memory
  96. Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks
  97. In-context Time Series Predictor
  98. MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
  99. LOVA3: Learning to Visual Question Answering, Asking and Assessment
  100. Creativity and Markov Decision Processes
  101. Data Augmentation Method Utilizing Template Sentences for Variable Definition Extraction
  102. EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
  103. Understanding the dynamics of the frequency bias in neural networks
  104. Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution
  105. Fast Bayesian Inference for Neutrino Non-Standard Interactions at Dark Matter Direct Detection Experiments
  106. AstroPT: Scaling Large Observation Models for Astronomy
  107. PILOT: Equivariant diffusion for pocket conditioned de novo ligand generation with multi-objective guidance via importance sampling
  108. How Does Bayes Error Limit Probabilistic Robust Accuracy
  109. AnalogCoder: Analog Circuit Design via Training-Free Code Generation
  110. SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
  111. High Rank Path Development: an approach of learning the filtration of stochastic processes
  112. Interpretable Price Bounds Estimation with Shape Constraints in Price Optimization
  113. BiMix: A Bivariate Data Mixing Law for Language Model Pretraining
  114. AutoCoder: Enhancing Code Large Language Model with textscAIEV-Instruct
  115. Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation
  116. Federated Online Adaptation for Deep Stereo
  117. NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections
  118. An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models
  119. PuzzleAvatar: Assembling 3D Avatars from Personal Albums
  120. Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
  121. Tele-Aloha: A Low-budget and High-authenticity Telepresence System Using Sparse RGB Cameras
  122. A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns
  123. Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
  124. Not All Language Model Features Are One-Dimensionally Linear
  125. Synergistic Global-space Camera and Human Reconstruction from Videos
  126. Privileged Sensing Scaffolds Reinforcement Learning
  127. PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
  128. Local Causal Discovery for Structural Evidence of Direct Discrimination
  129. Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling
  130. MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos
  131. Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distribution
  132. A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
  133. Analysis of Atom-level pretraining with Quantum Mechanics (QM) data for Graph Neural Networks Molecular property models
  134. Deep learning lattice gauge theories
  135. Camera Relocalization in Shadow-free Neural Radiance Fields
  136. Designing A Sustainable Marine Debris Clean-up Framework without Human Labels
  137. Scalable Optimization in the Modular Norm
  138. Implicit Personalization in Language Models: A Systematic Study
  139. Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
  140. Can LLMs Solve longer Math Word Problems Better?
  141. Generative Plant Growth Simulation from Sequence-Informed Environmental Conditions
  142. SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
  143. DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
  144. Masked Image Modelling for retinal OCT understanding
  145. Lessons from the Trenches on Reproducible Evaluation of Language Models
  146. Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning
  147. Smart Bilingual Focused Crawling of Parallel Documents
  148. Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
  149. Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations
  150. Evaluating Large Language Models for Public Health Classification and Extraction Tasks
  151. Neural Pfaffians: Solving Many Many-Electron Schr"odinger Equations
  152. Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
  153. Large language models can be zero-shot anomaly detectors for time series?
  154. Applied Machine Learning to Anomaly Detection in Enterprise Purchase Processes
  155. A Transformer-Based Approach for Smart Invocation of Automatic Code Completion
  156. Extreme Solar Flare Prediction Using Residual Networks with HMI Magnetograms and Intensitygrams
  157. MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs
  158. TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
  159. AnyLoss: Transforming Classification Metrics into Loss Functions
  160. Iterative Causal Segmentation: Filling the Gap between Market Segmentation and Marketing Strategy
  161. HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
  162. Subsampled Ensemble Can Improve Generalization Tail Exponentially
  163. Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning
  164. CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring
  165. GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
  166. CoPeD-Advancing Multi-Robot Collaborative Perception: A Comprehensive Dataset in Real-World Environments
  167. Embedding Compression for Efficient Re-Identification
  168. Intervention and Conditioning in Causal Bayesian Networks
  169. A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
  170. DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
  171. Convolutional Neural Network Model Observers Discount Signal-like Anatomical Structures During Search in Virtual Digital Breast Tomosynthesis Phantoms
  172. Decision-Focused Forecasting: A Differentiable Multistage Optimisation Architecture
  173. StyleX: A Trainable Metric for X-ray Style Distances
  174. HTN-Based Tutors: A New Intelligent Tutoring Framework Based on Hierarchical Task Networks
  175. Defining error accumulation in ML atmospheric simulators
  176. Towards Educator-Driven Tutor Authoring: Generative AI Approaches for Creating Intelligent Tutor Interfaces
  177. Evolution and learning in differentiable robots
  178. Zero-inflation in the Multivariate Poisson Lognormal Family
  179. OpFlowTalker: Realistic and Natural Talking Face Generation via Optical Flow Guidance
  180. Artificial Intelligence (AI) in Legal Data Mining
  181. Learning Multi-dimensional Human Preference for Text-to-Image Generation
  182. G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
  183. DreamText: High Fidelity Scene Text Synthesis
  184. Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference
  185. A Declarative System for Optimizing AI Workloads
  186. CityGPT: Towards Urban IoT Learning, Analysis and Interaction with Multi-Agent System
  187. Cascade of phase transitions in the training of Energy-based models
  188. Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
  189. Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond
  190. Invisible Backdoor Attack against Self-supervised Learning
  191. Overcoming the Challenges of Batch Normalization in Federated Learning
  192. Efficiency for Free: Ideal Data Are Transportable Representations
  193. Implicit In-context Learning
  194. Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization
  195. Efficient Medical Question Answering with Knowledge-Augmented Question Generation
  196. PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis
  197. Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
  198. Lagrangian Neural Networks for Reversible Dissipative Evolution
  199. Flatten Anything: Unsupervised Neural Surface Parameterization
  200. Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
  201. Event-based dataset for the detection and classification of manufacturing assembly tasks
  202. U-TELL: Unsupervised Task Expert Lifelong Learning
  203. Closed-form Solutions: A New Perspective on Solving Differential Equations
  204. exLong: Generating Exceptional Behavior Tests with Large Language Models
  205. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
  206. ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification
  207. Logical Characterizations of Recurrent Graph Neural Networks with Reals and Floats
  208. Controllable Continual Test-Time Adaptation
  209. A FAIR and Free Prompt-based Research Assistant
  210. Discretization of continuous input spaces in the hippocampal autoencoder
  211. Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs
  212. Linear Mode Connectivity in Differentiable Tree Ensembles
  213. Data Augmentation Techniques for Process Extraction from Scientific Publications
  214. Base of RoPE Bounds Context Length
  215. MAMOC: MRI Motion Correction via Masked Autoencoding
  216. SE3D: A Framework For Saliency Method Evaluation In 3D Imaging
  217. PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control
  218. Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
  219. Learning with Fitzpatrick Losses
  220. AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
  221. PrivCirNet: Efficient Private Inference via Block Circulant Transformation
  222. EHRMamba: Towards Generalizable and Scalable Foundation Models for Electronic Health Records
  223. Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet
  224. FUSE: Fast Unified Simulation and Estimation for PDEs
  225. Deep Learning Classification of Photoplethysmogram Signal for Hypertension Levels
  226. Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models
  227. Causal Effect Identification in a Sub-Population with Latent Variables
  228. A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction
  229. Nuclear Norm Regularization for Deep Learning
  230. This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
  231. Regressor-free Molecule Generation to Support Drug Response Prediction
  232. Exploring Alignment in Shared Cross-lingual Spaces
  233. Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
  234. Multistable Shape from Shading Emerges from Patch Diffusion
  235. AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
  236. Towards Privacy-Aware and Personalised Assistive Robots: A User-Centred Approach
  237. ArchesWeather: An efficient AI weather forecasting model at 1.5deg resolution
  238. Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
  239. Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
  240. Ghost-Stereo: GhostNet-based Cost Volume Enhancement and Aggregation for Stereo Matching Networks
  241. A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detection
  242. TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
  243. Towards Realistic Long-tailed Semi-supervised Learning in an Open World
  244. Prediction of cancer dynamics under treatment using Bayesian neural networks: A simulated study
  245. SIAVC: Semi-Supervised Framework for Industrial Accident Video Classification
  246. Explainable automatic industrial carbon footprint estimation from bank transaction classification using natural language processing
  247. Adaptive Runge-Kutta Dynamics for Spatiotemporal Prediction
  248. Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
  249. Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models
  250. Entrywise error bounds for low-rank approximations of kernel matrices
  251. Iterative Methods for Full-Scale Gaussian Process Approximations for Large Spatial Data
  252. End-to-End User-Defined Keyword Spotting using Shifted Delta Coefficients
  253. MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
  254. RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models
  255. Scalable Visual State Space Model with Fractal Scanning
  256. SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines
  257. Poisson Variational Autoencoder
  258. SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe
  259. Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition
  260. Generalization of Hamiltonian algorithms
  261. Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
  262. Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
  263. YOLOv10: Real-Time End-to-End Object Detection
  264. Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
  265. Domain-specific augmentations with resolution agnostic self-attention mechanism improves choroid segmentation in optical coherence tomography images
  266. JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression
  267. Worldwide Federated Training of Language Models
  268. Exploring the use of a Large Language Model for data extraction in systematic reviews: a rapid feasibility study
  269. DuEDL: Dual-Branch Evidential Deep Learning for Scribble-Supervised Medical Image Segmentation
  270. Bayesian Adaptive Calibration and Optimal Design
  271. LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks
  272. Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models
  273. Adaptive Gradient Clipping for Robust Federated Learning
  274. Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs
  275. When predict can also explain: few-shot prediction to select better neural latents
  276. Unraveling overoptimism and publication bias in ML-driven science
  277. A motion-based compression algorithm for resource-constrained video camera traps
  278. Proving Theorems Recursively
  279. Large Language Models for Explainable Decisions in Dynamic Digital Twins
  280. Investigating the Common Authorship of Signatures by Off-Line Automatic Signature Verification Without the Use of Reference Signatures
  281. Qubit-efficient Variational Quantum Algorithms for Image Segmentation
  282. Exact Gauss-Newton Optimization for Training Deep Neural Networks
  283. Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networks
  284. SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
  285. Instruction Tuning With Loss Over Instructions
  286. Explainable Few-shot Knowledge Tracing
  287. stl2vec: Semantic and Interpretable Vector Representation of Temporal Logic
  288. Evaluation of the Programming Skills of Large Language Models
  289. Capsule Network Projectors are Equivariant and Invariant Learners
  290. Emotion Identification for French in Written Texts: Considering their Modes of Expression as a Step Towards Text Complexity Analysis
  291. Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
  292. CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
  293. RoPINN: Region Optimized Physics-Informed Neural Networks
  294. Retrieval-Augmented Mining of Temporal Logic Specifications from Data
  295. Explaining Graph Neural Networks via Structure-aware Interaction Index
  296. Mixture of Public and Private Distributions in Imperfect Information Games
  297. Efficient Visual State Space Model for Image Deblurring
  298. RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian
  299. Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
  300. Hierarchical Salient Patch Identification for Interpretable Fundus Disease Localization
  301. LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
  302. Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
  303. Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
  304. Adaptive Retention & Correction: Test-Time Training for Continual Learning
  305. Smooth Pseudo-Labeling
  306. Improving Gloss-free Sign Language Translation by Reducing Representation Density
  307. Similarity-Navigated Conformal Prediction for Graph Neural Networks
  308. Graphcode: Learning from multiparameter persistent homology using graph neural networks
  309. Does context matter in digital pathology?
  310. Automatic diagnosis of cardiac magnetic resonance images based on semi-supervised learning
  311. Focus Anywhere for Fine-grained Multi-page Document Understanding
  312. Tuning-free Universally-Supervised Semantic Segmentation
  313. A New Method in Facial Registration in Clinics Based on Structure Light Images
  314. Variational Bayes for Federated Continual Learning
  315. Modeling Edge-Specific Node Features through Co-Representation Neural Hypergraph Diffusion
  316. Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
  317. SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation
  318. Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
  319. D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
  320. Exact Solution to Data-Driven Inverse Optimization of MILPs in Finite Time via Gradient-Based Methods
  321. Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
  322. Sparse L1-Autoencoders for Scientific Data Compression
  323. Multi-Representation Genetic Programming: A Case Study on Tree-based and Linear Representations
  324. A Gap in Time: The Challenge of Processing Heterogeneous IoT Data in Digitalized Buildings
  325. Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspective
  326. Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR
  327. Deep Learning Methods for Adjusting Global MFD Speed Estimations to Local Link Configurations
  328. Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
  329. Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
  330. Text-Based Correlation Matrix in Multi-Asset Allocation
  331. GCondenser: Benchmarking Graph Condensation
  332. M2ANET: Mobile Malaria Attention Network for efficient classification of plasmodium parasites in blood cells
  333. NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
  334. Harmony: A Joint Self-Supervised and Weakly-Supervised Framework for Learning General Purpose Visual Representations
  335. Language processing in humans and computers
  336. FloodDamageCast: Building Flood Damage Nowcasting with Machine Learning and Data Augmentation
  337. From Role-Play to Drama-Interaction: An LLM Solution
  338. Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports
  339. ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining
  340. Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models
  341. Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization
  342. Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making
  343. ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks
  344. Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds
  345. LG-VQ: Language-Guided Codebook Learning
  346. GLaD: Synergizing Molecular Graphs and Language Descriptors for Enhanced Power Conversion Efficiency Prediction in Organic Photovoltaic Devices
  347. Awesome Multi-modal Object Tracking
  348. Enhanced Object Tracking by Self-Supervised Auxiliary Depth Estimation Learning
  349. Graphlets correct for the topological information missed by random walks
  350. IB-AdCSCNet:Adaptive Convolutional Sparse Coding Network Driven by Information Bottleneck
  351. S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
  352. Fairness Hub Technical Briefs: Definition and Detection of Distribution Shift
  353. A Structure-Aware Framework for Learning Device Placements on Computation Graphs
  354. UzMorphAnalyser: A Morphological Analysis Model for the Uzbek Language Using Inflectional Endings
  355. Certified Robustness against Sparse Adversarial Perturbations via Data Localization
  356. Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
  357. Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication
  358. Multi-view Remote Sensing Image Segmentation With SAM priors
  359. Leveraging Semantic Segmentation Masks with Embeddings for Fine-Grained Form Classification
  360. Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
  361. Super Tiny Language Models
  362. A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data
  363. jp-evalb: Robust Alignment-based PARSEVAL Measures
  364. Real Time Deep Learning Weapon Detection Techniques for Mitigating Lone Wolf Attacks
  365. Minimum number of neurons in fully connected layers of a given neural network (the first approximation)
  366. Hyperspectral Image Dataset for Individual Penguin Identification
  367. Imagery as Inquiry: Exploring A Multimodal Dataset for Conversational Recommendation
  368. ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer Model
  369. Contribute to balance, wire in accordance: Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule
  370. Efficient Multitask Dense Predictor via Binarization
  371. Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs
  372. Automated Loss function Search for Class-imbalanced Node Classification
  373. One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
  374. Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?
  375. Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
  376. Learning Multimodal Confidence for Intention Recognition in Human-Robot Interaction
  377. Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers
  378. Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation
  379. Improving Generalization of Deep Neural Networks by Optimum Shifting
  380. Assessing the potential of deep learning for protein-ligand docking
  381. Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
  382. Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
  383. Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
  384. Attending to Topological Spaces: The Cellular Transformer
  385. Large Language Models Can Self-Correct with Key Condition Verification
  386. Solving 0-1 Integer Programs with Unknown Knapsack Constraints Using Membership Oracles
  387. Improved Canonicalization for Model Agnostic Equivariance
  388. High-dimensional Learning with Noisy Labels
  389. Advancing Transportation Mode Share Analysis with Built Environment: Deep Hybrid Models with Urban Road Network
  390. Learning to Transform Dynamically for Better Adversarial Transferability