mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 5 Sep 2024

239 papers

  1. On the Complexity of Neural Computation in SuperpositionMechanistic interpretability → Sparse autoencoder training and evaluation
  2. Visual Prompting in Multimodal Large Language Models: A SurveyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. Debiasing Text Safety Classifiers through a Fairness-Aware EnsembleLLM safety and security → Safety alignment, refusal and guardrails
  4. MAS4POI: a Multi-Agents Collaboration System for Next POI RecommendationLLM agents and tool use → Agentic recommender systems
  5. Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 SmallMechanistic interpretability → Sparse autoencoder training and evaluation
  6. Generating High Dimensional User-Specific Wireless Channels using Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  7. Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  8. On the Convergence Rates of Federated Q-Learning across Heterogeneous EnvironmentsDeep reinforcement learning methods → RL for energy, networks and operations
  9. Few-shot Adaptation of Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  10. Neural EntropyDiffusion models → Diffusion foundations and sampling
  11. DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic CompensationDiffusion models → Diffusion foundations and sampling
  12. Dynamics of Supervised and Reinforcement Learning in the Non-Linear PerceptronDeep reinforcement learning methods → Deep RL algorithms and representations
  13. Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?LLM safety and security → Membership inference attacks
  14. Differentiable Discrete Event Simulation for Queuing Network ControlDeep reinforcement learning methods → RL for energy, networks and operations
  15. TRACE-CS: A Hybrid Logic-LLM System for Explainable Course SchedulingLLM reasoning → Reasoning benchmarks and evaluation
  16. LLM-based multi-agent poetry generation in non-cooperative environmentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  17. On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  18. RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated ImagesDiffusion models → Diffusion and flow policies for robotics
  19. TCDiff: Triple Condition Diffusion Model with 3D Constraints for Stylizing Synthetic FacesDiffusion models → Image generation, text-to-image and editing
  20. Text-Guided Mixup Towards Long-Tailed Image CategorizationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  21. CHIRPs: Change-Induced Regret Proxy metrics for Lifelong Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  22. DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any ArchitectureDiffusion models → Diffusion foundations and sampling
  23. Have Large Vision-Language Models Mastered Art History?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  24. Blended Latent Diffusion under Attention Control for Real-World Video EditingDiffusion models → Video generation
  25. From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven AgentsLLM agents and tool use → Educational agents and math problem solving
  26. LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model PriorsDiffusion models → 3D, point cloud and scene generation
  27. Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image RestorationDiffusion models → Inverse problems and image restoration
  28. Neural HD Map Generation from Multiple Vectorized Tiles Locally Produced by Autonomous VehiclesEnd-to-end autonomous driving → End-to-end system architecture
  29. Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilitiesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  30. Rx Strategist: Prescription Verification using LLM Agents SystemLLM agents and tool use → Medical and scientific domain agents
  31. UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing ImagesState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  32. TG-LMM: Enhancing Medical Image Segmentation Accuracy through Text-Guided Large Multi-Modal ModelMultimodal LLMs / vision-language models → Medical vision-language models
  33. CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive TasksSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  34. Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine UnlearningDiffusion models → Robustness, privacy and adversarial aspects +1
  35. ELO-Rated Sequence Rewards: Advancing Reinforcement Learning ModelsDeep reinforcement learning methods → RL theory and sample complexity
  36. Interpretable mixture of experts for time series prediction under recurrent and non-recurrent conditionsMixture-of-experts → MoE for time series and graphs
  37. ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart UnderstandingMixture-of-experts → MoE large language models
  38. Robust synchronization and policy adaptation for networked heterogeneous agentsDeep reinforcement learning methods → Deep RL algorithms and representations
  39. OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous DrivingWorld models → World models for autonomous driving +2
  40. Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy ElicitationLLM reasoning → Prompting and chain-of-thought reasoning
  41. SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion ModelDiffusion models → Audio, speech and music
  42. E2CL: Exploration-based Error Correction Learning for Embodied AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  43. Robust Q-Learning under Corrupted RewardsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  44. State-space models are accurate and efficient neural operators for dynamical systemsState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  45. Why mamba is effective? Exploit Linear Transformer-Mamba Network for Multi-Modality Image FusionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  46. xLAM: A Family of Large Action Models to Empower AI Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  47. iSeg: An Iterative Refinement-based Framework for Training-free SegmentationDiffusion models → Medical imaging and segmentation
  48. TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal ConsiderationsLLM reasoning → Multimodal reasoning +1
  49. RoomDiffusion: A Specialized Diffusion Model in the Interior Design IndustryDiffusion models → 3D, point cloud and scene generation
  50. MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  51. InfraLib: Enabling Reinforcement Learning and Decision-Making for Large-Scale Infrastructure ManagementDeep reinforcement learning methods → RL for energy, networks and operations
  52. Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  53. Discovering Cyclists' Visual Preferences Through Shared Bike Trajectories and Street View Images Using Inverse Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  54. Shared Autonomy with IDA: Interventional Diffusion Assistance
  55. An Efficient Recommendation Model Based on Knowledge Graph Attention-Assisted Network (KGATAX)
  56. Reducing Bias in Deep Learning Optimization: The RSGDM Approach
  57. Deep Transfer Learning for Breast Cancer Classification
  58. Enhancing coastal water body segmentation with Landsat Irish Coastal Segmentation (LICS) dataset
  59. Optimizing Feature Selection with Genetic Algorithms: A Review of Methods and Applications
  60. Entity Extraction from High-Level Corruption Schemes via Large Language Models
  61. Shaping the Future of Endangered and Low-Resource Languages -- Our Role in the Age of LLMs: A Keynote at ECIR 2024
  62. CA-BERT: Leveraging Context Awareness for Enhanced Multi-Turn Chat Interaction
  63. Lightweight Transducer Based on Frame-Level Criterion
  64. Diffusion Map Autoencoder
  65. Memory-Optimized Once-For-All Network
  66. Simplex-enabled Safe Continual Learning Machine
  67. Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation
  68. Learning in Order! A Sequential Strategy to Learn Invariant Features for Multimodal Sentiment Analysis
  69. TropNNC: Structured Neural Network Compression Using Tropical Geometry
  70. HUMOS: Human Motion Model Conditioned on Body Shape
  71. Experimentation in Content Moderation using RWKV
  72. Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning
  73. Harnessing LLMs for Cross-City OD Flow Prediction
  74. A deep learning approach to wall-shear stress quantification: From numerical training to zero-shot experimental application
  75. Data-Efficient Generation for Dataset Distillation
  76. A Survey on Signed Graph Embedding: Methods and Applications
  77. Image Recognition for Garbage Classification Based on Pixel Distribution Learning
  78. The Role of Generative Systems in Historical Photography Management: A Case Study on Catalan Archives
  79. CACER: Clinical Concept Annotations for Cancer Events and Relations
  80. WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking
  81. Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models
  82. Understanding Fairness in Recommender Systems: A Healthcare Perspective
  83. Active Sampling of Interpolation Points to Identify Dominant Subspaces for Model Reduction
  84. Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
  85. MVTN: A Multiscale Video Transformer Network for Hand Gesture Recognition
  86. Recon-all-clinical: Cortical surface reconstruction and analysis of heterogeneous clinical brain MRI
  87. The Influence of Faulty Labels in Data Sets on Human Pose Estimation
  88. Multi-agent Path Finding for Mixed Autonomy Traffic Coordination
  89. Multi-Camera Industrial Open-Set Person Re-Identification and Tracking
  90. Ground-roll Separation From Land Seismic Records Based on Convolutional Neural Network
  91. Cost-Control in Display Advertising: Theory vs Practice
  92. Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?
  93. Sirius: Contextual Sparsity with Correction for Efficient LLMs
  94. Latent Space Energy-based Neural ODEs
  95. MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization
  96. Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption
  97. Sequence modeling of higher-order wave modes of binary black hole mergers
  98. PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
  99. How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
  100. Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization
All 239
  1. Mpox Screen Lite: AI-Driven On-Device Offline Mpox Screening for Low-Resource African Mpox Emergency Response
  2. Exploratory Visual Analysis for Increasing Data Readiness in Artificial Intelligence Projects
  3. Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detection
  4. Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
  5. Foundation Model or Finetune? Evaluation of few-shot semantic segmentation for river pollution
  6. WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
  7. Attention Heads of Large Language Models: A Survey
  8. ArtiFade: Learning to Generate High-quality Subject from Blemished Images
  9. Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
  10. Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entry
  11. Planning In Natural Language Improves LLM Search For Code Generation
  12. A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization
  13. Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation
  14. RAG based Question-Answering for Contextual Response Prediction System
  15. A Different Level Text Protection Mechanism With Differential Privacy
  16. Iterative thresholding for non-linear learning in the strong varepsilon-contamination model
  17. LAST: Language Model Aware Speech Tokenization
  18. Classification and Prediction of Heart Diseases using Machine Learning Algorithms
  19. View-Invariant Policy Learning via Zero-Shot Novel View Synthesis
  20. Predicting quantum channels over general product distributions
  21. A New First-Order Meta-Learning Algorithm with Convergence Guarantees
  22. Practical Forecasting of Cryptocoins Timeseries using Correlation Patterns
  23. Wind turbine condition monitoring based on intra- and inter-farm federated learning
  24. A method to benchmark high-dimensional process drift detection
  25. A Fused Large Language Model for Predicting Startup Success
  26. Threat Classification on Deployed Optical Networks Using MIMO Digital Fiber Sensing, Wavelets, and Machine Learning
  27. Weather-Adaptive Multi-Step Forecasting of State of Polarization Changes in Aerial Fibers Using Wavelet Neural Networks
  28. The representation landscape of few-shot learning and fine-tuning in large language models
  29. A DNN Biophysics Model with Topological and Electrostatic Features
  30. Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks
  31. Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization
  32. Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG
  33. Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching
  34. Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction
  35. Beyond Model Interpretability: Socio-Structural Explanations in Machine Learning
  36. Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers
  37. DART2: a robust multiple testing method to smartly leverage helpful or misleading ancillary information
  38. 1 Modular Parallel Manipulator for Long-Term Soft Robotic Data Collection
  39. VFLGAN-TS: Vertical Federated Learning-based Generative Adversarial Networks for Publication of Vertically Partitioned Time-Series Data
  40. SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing
  41. A practical approach to evaluating the adversarial distance for machine learning classifiers
  42. Multimodal Laryngoscopic Video Analysis for Assisted Diagnosis of Vocal Fold Paralysis
  43. Cost Estimation in Unit Commitment Problems Using Simulation-Based Inference
  44. 100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances
  45. MaskVal: Simple but Effective Uncertainty Quantification for 6D Pose Estimation
  46. Unified Framework for Pre-trained Neural Network Compression via Decomposition and Optimized Rank Selection
  47. Organized Grouped Discrete Representation for Object-Centric Learning
  48. The Power of Second Chance: Personalized Submodular Maximization with Two Candidates
  49. Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift
  50. Risk-based Calibration for Generative Classifiers
  51. Use of triplet loss for facial restoration in low-resolution images
  52. FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
  53. Tissue Concepts: supervised foundation models in computational pathology
  54. LMLT: Low-to-high Multi-Level Vision Transformer for Image Super-Resolution
  55. A Physics-Informed Machine Learning Approach for Solving Distributed Order Fractional Differential Equations
  56. Survey of Data-driven Newsvendor: Unified Analysis and Spectrum of Achievable Regrets
  57. Quality Perceptions and Intended Engagement in Response to AI-Generated and AI-Assisted News
  58. Maximum likelihood inference for high-dimensional problems with multiaffine variable relations
  59. Distributionally Robust Optimisation with Bayesian Ambiguity Sets
  60. Sparsifying Parametric Models with L0 Regularization
  61. ScreenMark: Watermarking Arbitrary Visual Content on Screen
  62. LLM-based event abstraction and integration for IoT-sourced logs
  63. Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
  64. Panopticon: a novel deep learning model to detect single transit events with no prior data filtering in PLATO light curves
  65. Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability
  66. LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones
  67. Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks
  68. How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes
  69. Automatic occlusion removal from 3D maps for maritime situational awareness
  70. KiloBot: A Programming Language for Deploying Perception-Guided Industrial Manipulators at Scale
  71. Shuffle Vision Transformer: Lightweight, Fast and Efficient Recognition of Driver Facial Expression
  72. A Key-Driven Framework for Identity-Preserving Face Anonymization
  73. Reinforcement Learning Approach to Optimizing Profilometric Sensor Trajectories for Surface Inspection
  74. Weight Conditioning for Smooth Optimization of Neural Networks
  75. mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding
  76. KAN See In the Dark
  77. Game On: Towards Language Models as RL Experimenters
  78. Make Graph-based Referring Expression Comprehension Great Again through Expression-guided Dynamic Gating and Regression
  79. Hardware Acceleration of LLMs: A comprehensive survey and comparison
  80. aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio
  81. Leveraging Large Language Models through Natural Language Processing to provide interpretable Machine Learning predictions of mental deterioration in real time
  82. TBConvL-Net: A Hybrid Deep Learning Architecture for Robust Medical Image Segmentation
  83. Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling
  84. Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
  85. MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice
  86. Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images
  87. Sketch: A Toolkit for Streamlining LLM Operations
  88. Estimating Indoor Scene Depth Maps from Ultrasonic Echoes
  89. Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
  90. Normal forms in Virus Machines
  91. YOLO-PPA based Efficient Traffic Sign Detection for Cruise Control in Autonomous Driving
  92. Towards training digitally-tied analog blocks via hybrid gradient computation
  93. Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
  94. Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems
  95. Bringing the RT-1-X Foundation Model to a SCARA robot
  96. N-gram Prediction and Word Difference Representations for Language Modeling
  97. LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts
  98. iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models
  99. Tensor network square root Kalman filter for online Gaussian process regression
  100. Recent Advances in Attack and Defense Approaches of Large Language Models
  101. Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision
  102. In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search
  103. GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding
  104. Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard
  105. Granular-ball Representation Learning for Deep CNN on Learning with Label Noise
  106. SpinMultiNet: Neural Network Potential Incorporating Spin Degrees of Freedom with Multi-Task Learning
  107. Gr-IoU: Ground-Intersection over Union for Robust Multi-Object Tracking with 3D Geometric Constraints
  108. Dual-TSST: A Dual-Branch Temporal-Spectral-Spatial Transformer Model for EEG Decoding
  109. Multiple weather images restoration using the task transformer and adaptive mixup strategy
  110. UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking
  111. DiffGrad for Physics-Informed Neural Networks
  112. Preserving Empirical Probabilities in BERT for Small-sample Clinical Entity Recognition
  113. Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection
  114. Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation
  115. Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration
  116. FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks
  117. Content Moderation by LLM: From Accuracy to Legitimacy
  118. Application Research On Real-Time Perception Of Device Performance Status
  119. Optimizing 3D Gaussian Splatting for Sparse Viewpoint Scene Reconstruction
  120. Bi-capacity Choquet Integral for Sensor Fusion with Label Uncertainty
  121. Pricing American Options using Machine Learning Algorithms
  122. An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification
  123. Active Fake: DeepFake Camouflage
  124. PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning
  125. How noise affects memory in linear recurrent networks
  126. Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers
  127. Machine learning-based algorithms for at-home respiratory disease monitoring and respiratory assessment
  128. Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem
  129. Continual Robot Skill and Task Learning via Dialogue
  130. RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifiers
  131. MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models
  132. Standing on the shoulders of giants
  133. Non-stationary and Sparsely-correlated Multi-output Gaussian Process with Spike-and-Slab Prior
  134. Addressing the Gaps in Early Dementia Detection: A Path Towards Enhanced Diagnostic Models through Machine Learning
  135. Causal Temporal Representation Learning with Nonstationary Sparse Transition
  136. Towards Autonomous Cybersecurity: An Intelligent AutoML Framework for Autonomous Intrusion Detection
  137. GraphEx: A Graph-based Extraction Method for Advertiser Keyphrase Recommendation
  138. The AdEMAMix Optimizer: Better, Faster, Older
  139. A New Forward Discriminant Analysis Framework Based On Pillai's Trace and ULDA