mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 22 Jan 2025

213 papers

  1. AI Agentic workflows and Enterprise APIs: Adapting API architectures for the age of AI agentsLLM agents and tool use → Software engineering coding agents
  2. UAV-assisted Internet of Vehicles: A Framework Empowered by Reinforcement Learning and BlockchainDeep reinforcement learning methods → RL for robot navigation and UAV control
  3. FishBargain: An LLM-Empowered Bargaining Agent for Online Fleamarket Platform SellersLLM agents and tool use → Social simulation and multi-agent debate
  4. InsTex: Indoor Scenes Stylized Texture SynthesisDiffusion models → 3D, point cloud and scene generation
  5. OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context GenerationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. State Combinatorial Generalization In Decision Making With Conditional Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  7. Data Matters Most: Auditing Social Bias in Contrastive Vision Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  8. UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion PriorDiffusion models → Inverse problems and image restoration
  9. Graph Representation Learning with Diffusion Generative ModelsDiffusion models → Flow matching, time series and science
  10. A Hierarchical Reinforcement Learning Framework for Multi-UAV Combat Using Leader-Follower StrategyDeep reinforcement learning methods → RL for robot navigation and UAV control
  11. Accelerate High-Quality Diffusion Models with Inner Loop FeedbackDiffusion models → Diffusion foundations and sampling
  12. Robust Representation Consistency Model via Contrastive DenoisingDiffusion models → Robustness, privacy and adversarial aspects
  13. Orchid: Image Latent Diffusion for Joint Appearance and Geometry GenerationDiffusion models → 3D, point cloud and scene generation
  14. Belief-Contraction-Driven Active Inverse Source Localization and CharacterizationDeep reinforcement learning methods → RL theory and sample complexity
  15. Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and AlignmentLLM reasoning → Reasoning for agents, planning and code +1
  16. Autonomy-of-Experts ModelsMixture-of-experts → MoE large language models
  17. AdaWM: Adaptive World Model based Planning for Autonomous DrivingWorld models → World models for autonomous driving +2
  18. Beyond the Lungs: Extending the Field of View in Chest CT with Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
  19. Does Table Source Matter? Benchmarking and Improving Multimodal Scientific Table Understanding and ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  20. Optimizing Return Distributions with Distributional Dynamic ProgrammingDeep reinforcement learning methods → RL theory and sample complexity
  21. MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward HackingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  22. PairJudge RM: Perform Best-of-N Sampling with Knockout TournamentLLM reasoning → Test-time compute and efficient thinking +1
  23. Ehrenfeucht-Haussler Rank and Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
  24. An Offline Multi-Agent Reinforcement Learning Framework for Radio Resource ManagementOffline RL and imitation learning from data → Offline multi-agent RL
  25. Low-dimensional adaptation of diffusion models: Convergence in total variationDiffusion models → Diffusion foundations and sampling
  26. LiT: Delving into a Simple Linear Diffusion Transformer for Image GenerationDiffusion models → Diffusion foundations and sampling
  27. Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer InferenceEfficient LLM inference and serving → Prompt and context compression
  28. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  29. Offline Diffusion Policy for Multi-User Delay-Constrained SchedulingDiffusion models → Diffusion and flow policies for robotics +1
  30. 3D Object Manipulation in a Single Image using Generative ModelsDiffusion models → 3D, point cloud and scene generation
  31. FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D SpacesLLM agents and tool use → Multimodal and embodied agents
  32. Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual FeedbackLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  33. Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  34. CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack SegmentationDiffusion models → Flow matching, time series and science
  35. ACEBench: Who Wins the Match Point in Tool Usage?LLM agents and tool use → Tool learning and function calling
  36. AMM-Diff: Adaptive Multi-Modality Diffusion Network for Missing Modality ImputationDiffusion models → Medical imaging and segmentation
  37. Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back HomeRetrieval-augmented generation → RAG robustness and adaptive retrieval
  38. FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image RestorationDiffusion models → Inverse problems and image restoration
  39. To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
  40. Certified Guidance for Planning with Deep Generative ModelsDiffusion models → Diffusion and flow policies for robotics
  41. Revisit Self-Debugging with Self-Generated Tests for Code GenerationSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  42. Generating Diverse Q&A Benchmarks for RAG Evaluation with DataMorganaRetrieval-augmented generation → RAG pipeline design and evaluation
  43. On Generalization and Distributional Update for Mimicking Observations with Adequate ExplorationOffline RL and imitation learning from data → Imitation learning methods
  44. Patent Figure Classification using Large Vision-language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. Online Preference Alignment for Language Models via Count-based ExplorationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  46. HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage EstimationDeep reinforcement learning methods → RL theory and sample complexity
  47. Training Dialogue Systems by AI Feedback for Improving Overall Dialogue ImpressionLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  48. Extracting General-use Transformers for Low-resource Languages via Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  49. Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal BehaviorsOffline RL and imitation learning from data → Inverse reinforcement learning
  50. Deep Reinforcement Learning with Hybrid Intrinsic Reward ModelLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  51. Adaptive Data Exploitation in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  52. Image Motion Blur Removal in the Temporal Dimension with Video Diffusion ModelsDiffusion models → Inverse problems and image restoration
  53. BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASRMixture-of-experts → Expert routing strategies
  54. Kimi k1.5: Scaling Reinforcement Learning with LLMsLLM reasoning → Reinforcement learning for reasoning
  55. O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning PruningLLM reasoning → Test-time compute and efficient thinking
  56. ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented RealityMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  57. Infinite Time Turing Machines and their Applications
  58. MapColorAI: Designing Contextually Relevant Choropleth Map Color Schemes Using a Large Language Model
  59. Development of an Inclusive Educational Platform Using Open Technologies and Machine Learning: A Case Study on Accessibility Enhancement
  60. GPUs, CPUs, and... NICs: Rethinking the Network's Role in Serving Complex AI Pipelines
  61. Data Science Students Perspectives on Learning Analytics: An Application of Human-Led and LLM Content Analysis
  62. Knowledge Tracing in Programming Education Integrating Students' Questions
  63. Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Management
  64. Information-theoretic Bayesian Optimization: Survey and Tutorial
  65. Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning
  66. Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
  67. Advanced Physics-Informed Neural Network with Residuals for Solving Complex Integral Equations
  68. Blockchain-based Crowdsourced Deep Reinforcement Learning as a Service
  69. Foundation Models for CPS-IoT: Opportunities and Challenges
  70. CAND: Cross-Domain Ambiguity Inference for Early Detecting Nuanced Illness Deterioration
  71. Multivariate Time Series Anomaly Detection by Capturing Coarse-Grained Intra- and Inter-Variate Dependencies
  72. An Ensemble Model with Attention Based Mechanism for Image Captioning
  73. 3DGS2: Near Second-order Converging 3D Gaussian Splatting
  74. A Spatio-temporal Graph Network Allowing Incomplete Trajectory Input for Pedestrian Trajectory Prediction
  75. Synthetic CT image generation from CBCT: A Systematic Review
  76. GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting
  77. Patch-Based and Non-Patch-Based inputs Comparison into Deep Neural Models: Application for the Segmentation of Retinal Diseases on Optical Coherence Tomography Volumes
  78. Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation
  79. FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis
  80. MEDFORM: A Foundation Model for Contrastive Learning of CT Imaging and Clinical Numeric Data in Multi-Cancer Analysis
  81. T-Graphormer: Using Transformers for Spatiotemporal Forecasting
  82. Enhancing Robust Fairness via Confusional Spectral Regularization
  83. Hybrid Two-Stage Reconstruction of Multiscale Subsurface Flow with Physics-informed Residual Connected Neural Operator
  84. Exploring the Technology Landscape through Topic Modeling, Expert Involvement, and Reinforcement Learning
  85. Multimodal AI on Wound Images and Clinical Notes for Home Patient Referral
  86. Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
  87. MLPs at the EOC: Spectrum of the NTK
  88. Enhancing Multi-Attribute Fairness in Healthcare Predictive Modeling
  89. SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
  90. SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
  91. Revisiting Data Augmentation for Ultrasound Images
  92. Map Prediction and Generative Entropy for Multi-Agent Exploration
  93. Topological constraints on self-organisation in locally interacting systems
  94. MONA: Moving Object Detection from Videos Shot by Dynamic Camera
  95. Learning in Log-Domain: Subthreshold Analog AI Accelerator Based on Stochastic Gradient Descent
  96. QuFeX: Quantum feature extraction module for hybrid quantum-classical deep neural networks
  97. AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks
  98. Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems
  99. Forecasting of Bitcoin Prices Using Hashrate Features: Wavelet and Deep Stacking Approach
  100. Applications and Challenges of AI and Microscopy in Life Science Research: A Review
All 213
  1. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
  2. Neural Radiance Fields for the Real World: A Survey
  3. A Rate-Distortion Framework for Summarization
  4. Guaranteed Recovery of Unambiguous Clusters
  5. Boosting MCTS with Free Energy Minimization
  6. Evolution and The Knightian Blindspot of Machine Learning
  7. CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization
  8. Robust Body Composition Analysis by Generating 3D CT Volumes from Limited 2D Slices
  9. SMART-Vision: Survey of Modern Action Recognition Techniques in Vision
  10. A polynomial formula for the perspective four points problem
  11. vSTMD: Visual Motion Detection for Extremely Tiny Target at Various Velocities
  12. One-Class Domain Adaptation via Meta-Learning
  13. Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes
  14. TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
  15. A Probabilistic Model for Non-Contrastive Learning
  16. Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis
  17. Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs
  18. Paper Quality Assessment based on Individual Wisdom Metrics from Open Peer Review
  19. The regret lower bound for communicating Markov Decision Processes
  20. Learning accurate rigid registration for longitudinal brain MRI from synthetic data
  21. Deep Learning-Based Image Recovery and Pose Estimation for Resident Space Objects
  22. UniUIR: Considering Underwater Image Restoration as An All-in-One Learner
  23. Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities
  24. FlanEC: Exploring Flan-T5 for Post-ASR Error Correction
  25. Galois groups of polynomials and neurosymbolic networks
  26. OnionEval: An Unified Evaluation of Fact-conflicting Hallucination for Small-Large Language Models
  27. MorphoSkel3D: Morphological Skeletonization of 3D Point Clouds for Informed Sampling in Object Classification and Retrieval
  28. Accessible Smart Contracts Verification: Synthesizing Formal Models with Tamed LLMs
  29. It's complicated. The relationship of algorithmic fairness and non-discrimination provisions for high-risk systems in the EU AI Act
  30. A Novel Tracking Framework for Devices in X-ray Leveraging Supplementary Cue-Driven Self-Supervised Features
  31. Fixed-Budget Change Point Identification in Piecewise Constant Bandits
  32. GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
  33. Multifractal hopscotch in "Hopscotch" by Julio Cortazar
  34. Punctuation patterns in "Finnegans Wake" by James Joyce are largely translation-invariant
  35. Ontology-Enhanced Educational Annotation Activities
  36. Correctness Assessment of Code Generated by Large Language Models Using Internal Representations
  37. DynamicEarth: How Far are We from Open-Vocabulary Change Detection?
  38. Longitudinal Missing Data Imputation for Predicting Disability Stage of Patients with Multiple Sclerosis
  39. Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
  40. A Selective Homomorphic Encryption Approach for Faster Privacy-Preserving Federated Learning
  41. PreciseCam: Precise Camera Control for Text-to-Image Generation
  42. Architectural Fusion Through Contextual Partitioning in Large Language Models: A Novel Approach to Parameterized Knowledge Integration
  43. Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi
  44. DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning
  45. Irrational Complex Rotations Empower Low-bit Optimizers
  46. Learning Graph Node Embeddings by Smooth Pair Sampling
  47. Advanced deep architecture pruning using single filter performance
  48. WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge
  49. Drone Carrier: An Integrated Unmanned Surface Vehicle for Autonomous Inspection and Intervention in GNSS-Denied Maritime Environment
  50. As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Making
  51. Mutation-Guided LLM-based Test Generation at Meta
  52. HierPromptLM: A Pure PLM-based Framework for Representation Learning on Heterogeneous Text-rich Networks
  53. Data-and-Semantic Dual-Driven Spectrum Map Construction for 6G Spectrum Management
  54. GAMED-Snake: Gradient-aware Adaptive Momentum Evolution Deep Snake Model for Multi-organ Segmentation
  55. A transformer-based deep q learning approach for dynamic load balancing in software-defined networks
  56. Open or Closed LLM for Lesser-Resourced Languages? Lessons from Greek
  57. Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks
  58. Unveiling Zero-Space Detection: A Novel Framework for Autonomous Ransomware Identification in High-Velocity Environments
  59. Machine Learning Modeling for Multi-order Human Visual Motion Processing
  60. Hybrid Losses for Hierarchical Embedding Learning
  61. Generation of Standardized E-Learning Contents from Digital Medical Collections
  62. Data re-uploading in Quantum Machine Learning for time series: application to traffic forecasting
  63. Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation
  64. LLMs as Repositories of Factual Knowledge: Limitations and Solutions
  65. Non-adaptive Learning of Random Hypergraphs with Queries
  66. On Tradeoffs in Learning-Augmented Algorithms
  67. NExtLong: Toward Effective Long-Context Training without Long Documents
  68. Modality Unified Attack for Omni-Modality Person Re-Identification
  69. Conformal Prediction of Classifiers with Many Classes based on Noisy Labels
  70. Singular leaning coefficients and efficiency in learning theory
  71. EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering
  72. Multiscale Training of Convolutional Neural Networks
  73. Stability and Generalization of Quantum Neural Networks
  74. Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning
  75. GRAMA: Adaptive Graph Autoregressive Moving Average Models
  76. A Call for Critically Rethinking and Reforming Data Analysis in Empirical Software Engineering
  77. Anomaly Detection in Double-entry Bookkeeping Data by Federated Learning System with Non-model Sharing Approach
  78. Experimentally validated quantum-secure federated learning over a multi-user quantum network
  79. REX: Causal discovery based on machine learning and explainability techniques
  80. The Marginal Importance of Distortions and Alignment in CASSI systems
  81. Combining Knowledge Graph and LLMs for Enhanced Zero-shot Visual Question Answering
  82. Growth strategies for arbitrary DAG neural architectures
  83. IC-Cache: Efficient Large Language Model Serving via In-context Caching
  84. Can masking background and object reduce static bias for zero-shot action recognition?
  85. Manifold learning and optimization using tangent space proxies
  86. Celo: Training Versatile Learned Optimizers on a Compute Diet
  87. NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
  88. Sequential Change Point Detection via Denoising Score Matching
  89. Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
  90. PPO-Based Vehicle Control for Ramp Merging Scheme Assisted by Enhanced C-V2X
  91. The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories
  92. Current Opinions on Memristor-Accelerated Machine Learning Hardware
  93. Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts
  94. DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform
  95. Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learning
  96. TeD-Loc: Text Distillation for Weakly Supervised Object Localization
  97. Knowledge-Driven Federated Graph Learning on Model Heterogeneity
  98. Towards Robust Multi-tab Website Fingerprinting
  99. Quantification of Large Language Model Distillation
  100. Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?
  101. GATE: Adaptive Learning with Working Memory by Information Gating in Multi-lamellar Hippocampal Formation
  102. T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
  103. Low-Dimensional Representation-Driven TSK Fuzzy System for Feature Selection
  104. On Accelerating Deep Neural Network Mutation Analysis by Neuron and Mutant Clustering
  105. Multi-Instance Partial-Label Learning with Margin Adjustment
  106. Adapting OpenAI's CLIP Model for Few-Shot Image Inspection in Manufacturing Quality Control: An Expository Case Study with Multiple Application Examples
  107. A Unified Invariant Learning Framework for Graph Classification
  108. FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling
  109. Ultralow-dimensionality reduction for identifying critical transitions by spatial-temporal PCA
  110. Leveraging LLMs to Create a Haptic Devices' Recommendation System
  111. Structural and mechanical properties of W-Cu compounds characterized by a neural-network-based potential
  112. Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review
  113. Generalization Performance of Hypergraph Neural Networks