mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 4 Feb 2024

198 papers

  1. Can Large Language Models Learn Independent Causal Mechanisms?LLM reasoning → Causal reasoning in LLMs
  2. A Safe Reinforcement Learning driven Weights-varying Model Predictive Control for Autonomous Vehicle Motion ControlEnd-to-end autonomous driving → Reinforcement learning for driving +1
  3. The Virtues of Pessimism in Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
  4. FCoReBench: Can Large Language Models Solve Challenging First-Order Combinatorial Reasoning Problems?LLM reasoning → Mathematical reasoning
  5. Accelerating Inverse Reinforcement Learning with Expert BootstrappingOffline RL and imitation learning from data → Inverse reinforcement learning
  6. DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image EditingDiffusion models → Image generation, text-to-image and editing
  7. Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  8. LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  9. CompeteSMoE -- Effective Training of Sparse Mixture of Experts via CompetitionMixture-of-experts → Expert routing strategies
  10. Unifying Generation and Prediction on Graphs with Latent Graph DiffusionDiffusion models → Flow matching, time series and science
  11. VM-UNet: Vision Mamba UNet for Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  12. BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  13. DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory StitchingOffline RL and imitation learning from data → Offline RL algorithms
  14. Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  15. Hybrid-Prediction Integrated Planning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  16. Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  17. Aligner: Efficient Alignment by Learning to CorrectLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  18. Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection RemovalDiffusion models → Inverse problems and image restoration
  20. Interference-Aware Emergent Random Access Protocol for Downlink LEO Satellite NetworksDeep reinforcement learning methods → Multi-agent reinforcement learning
  21. Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic FeedbackDiffusion models → Diffusion foundations and sampling
  22. Enhance Reasoning for Large Language Models in the Game WerewolfLLM reasoning → Reasoning for agents, planning and code +1
  23. INViT: A Generalizable Routing Problem Solver with Invariant Nested View TransformerDeep reinforcement learning methods → RL for games and combinatorial optimization
  24. Your Diffusion Model is Secretly a Certifiably Robust ClassifierDiffusion models → Robustness, privacy and adversarial aspects
  25. Jailbreaking Attack against Multimodal Large Language ModelLLM safety and security → Vision-language and text-to-image safety
  26. Navigating the Peril of Generated Alternative Facts: A ChatGPT-4 Fabricated Omega Variant Case as a Cautionary Tale in Medical Misinformation
  27. FoldToken: Learning Protein Language via Vector Quantization and Beyond
  28. COMPRER: A Multimodal Multi-Objective Pretraining Framework for Enhanced Medical Image Representation
  29. CoRaiS: Lightweight Real-Time Scheduler for Multi-Edge Cooperative Computing
  30. Diffusion Model-Based Multiobjective Optimization for Gasoline Blending Scheduling
  31. MemFlow: A Lightweight Forward Memorizing Framework for Quick Domain Adaptive Feature Mapping
  32. Learning Style Identification Using Semi-Supervised Self-Taught Labeling
  33. Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation
  34. Correlational Lagrangian Schr"odinger Bridge: Learning Dynamics with Population-Level Regularization
  35. Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
  36. Custom IMU-Based Wearable System for Robust 2.4 GHz Wireless Human Body Parts Orientation Tracking and 3D Movement Visualization on an Avatar
  37. A Physiological Sensor-Based Android Application Synchronized with a Driving Simulator for Driver Monitoring
  38. Conversational Crowdsensing: A Parallel Intelligence Powered Novel Sensing Approach
  39. Using remotely sensed data for air pollution assessment
  40. A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network
  41. Nature-Inspired Local Propagation
  42. A comparative study on wearables and single-camera video for upper-limb out-of-thelab activity recognition with different deep learning architectures
  43. Accelerating PDE Data Generation via Differential Operator Action in Solution Space
  44. Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
  45. A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints
  46. EasyFS: an Efficient Model-free Feature Selection Framework via Elastic Transformation of Features
  47. idMotif: An Interactive Motif Identification in Protein Sequences
  48. Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniques
  49. Comparative Analysis of Kinect-Based and Oculus-Based Gaze Region Estimation Methods in a Driving Simulator
  50. A Survey on Data Selection for LLM Instruction Tuning
  51. History of generative Artificial Intelligence (AI) chatbots: past, present, and future development
  52. Large Language Model for Table Processing: A Survey
  53. UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing
  54. PixelGen: Rethinking Embedded Camera Systems
  55. Delivery Optimized Discovery in Behavioral User Segmentation under Budget Constraint
  56. Overcoming Order in Autoregressive Graph Generation
  57. A generalized decision tree ensemble based on the NeuralNetworks architecture: Distributed Gradient Boosting Forest (DGBF)
  58. Adolescent relational behaviour and the obesity pandemic: A descriptive study applying social network analysis and machine learning techniques
  59. Survival and grade of the glioma prediction using transfer learning
  60. MCU-Net: A Multi-prior Collaborative Deep Unfolding Network with Gates-controlled Spatial Attention for Accelerated MR Image Reconstruction
  61. Entire Chain Uplift Modeling with Context-Enhanced Learning for Intelligent Marketing
  62. Permutation-based Inference for Variational Learning of Directed Acyclic Graphs
  63. LLM-Enhanced Data Management
  64. "It's how you do things that matters": Attending to Process to Better Serve Indigenous Communities with Language Technologies
  65. C^*-Algebraic Machine Learning: Moving in a New Direction
  66. Key-Graph Transformer for Image Restoration
  67. Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity
  68. GIRT-Model: Automated Generation of Issue Report Templates
  69. Learning to Understand: Identifying Interactions via the M"obius Transform
  70. PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
  71. Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network
  72. Position bias in features
  73. Enhancing Transformer RNNs with Multiple Temporal Perspectives
  74. Efficient Market Dynamics: Unraveling Informational Efficiency in UK Horse Racing Betting Markets Through Betfair's Time Series Analysis
  75. DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
  76. Understanding Addition and Subtraction in Transformers
  77. Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition
  78. Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach
  79. Dual Interior Point Optimization Learning
  80. Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy Environments
  81. Unified Training of Universal Time Series Forecasting Transformers
  82. On the performance of phonetic algorithms in microtext normalization
  83. Controller Synthesis from Noisy-Input Noisy-Output Data
  84. ClipFormer: Key-Value Clipping of Transformers on Memristive Crossbars for Write Noise Mitigation
  85. Impact of PSF misestimation and galaxy population bias on precision shear measurement using a CNN
  86. Spatio-temporal Prompting Network for Robust Video Feature Extraction
  87. A Quantitative Discourse Analysis of Asian Workers in the US Historical Newspapers
  88. Gazebo Plants: Simulating Plant-Robot Interaction with Cosserat Rods
  89. On the Complexity of Finite-Sum Smooth Optimization under the Polyak-Lojasiewicz Condition
  90. STAGE: Scalable and Traversability-Aware Graph based Exploration Planner for Dynamically Varying Environments
  91. A Truly Joint Neural Architecture for Segmentation and Parsing
  92. Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning
  93. NavHint: Vision and Language Navigation Agent with a Hint Generator
  94. Enhancing Robustness in Biomedical NLI Models: A Probing Approach for Clinical Trials
  95. A new approach for imprecise probabilities
  96. High-Quality Entity Segmentation and Grounding
  97. DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers
  98. Neur2BiLO: Neural Bilevel Optimization
  99. Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks
  100. Are Large Language Models Table-based Fact-Checkers?
All 198
  1. "What's my model inside of?": Exploring the role of environments for grounded natural language understanding
  2. Integration of cognitive tasks into artificial general intelligence test for large models
  3. Classification of Tennis Actions Using Deep Learning
  4. Knowledge Generation for Zero-shot Knowledge-based VQA
  5. Embedding Non-Distortive Cancelable Face Template Generation
  6. Absolute convergence and error thresholds in non-active adaptive sampling
  7. SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving
  8. Adaptive scheduling for adaptive sampling in POS taggers construction
  9. Modeling of learning curves with applications to pos tagging
  10. Deep Supervision by Gaussian Pseudo-label-based Morphological Attention for Abdominal Aorta Segmentation in Non-Contrast CTs
  11. Early stopping by correlating online indicators in neural networks
  12. PoCo: Policy Composition from and for Heterogeneous Robot Learning
  13. Device Scheduling and Assignment in Hierarchical Federated Learning for Internet of Things
  14. GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
  15. Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
  16. Robot Trajectron: Trajectory Prediction-based Shared Control for Robot Manipulation
  17. Fully Differentiable Correlation-driven 2D/3D Registration for X-ray to CT Image Fusion
  18. Weisfeiler Leman for Euclidean Equivariant Machine Learning
  19. Why are hyperbolic neural networks effective? A study on hierarchical representation capability
  20. TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling
  21. Deep Spectral Improvement for Unsupervised Image Instance Segmentation
  22. Fast Peer Adaptation with Context-aware Exploration
  23. A Graph is Worth K Words: Euclideanizing Graph using Pure Transformer
  24. A Fast Method for Lasso and Logistic Lasso
  25. Review of multimodal machine learning approaches in healthcare
  26. On Minimum Trace Factor Analysis -- An Old Song Sung to a New Tune
  27. tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
  28. On the Role of Initialization on the Implicit Bias in Deep Linear Networks
  29. AI Art Neural Constellation: Revealing the Collective and Contrastive State of AI-Generated and Human Art
  30. XAI-CF -- Examining the Role of Explainable Artificial Intelligence in Cyber Forensics
  31. Surfing the modeling of PoS taggers in low-resource scenarios
  32. Breaking MLPerf Training: A Case Study on Optimizing BERT
  33. LQER: Low-Rank Quantization Error Reconstruction for LLMs
  34. BECLR: Batch Enhanced Contrastive Few-Shot Learning
  35. A Momentum Accelerated Algorithm for ReLU-based Nonlinear Matrix Decomposition
  36. TopoX: A Suite of Python Packages for Machine Learning on Topological Domains
  37. Fast and interpretable Support Vector Classification based on the truncated ANOVA decomposition
  38. Uncertainty-Aware Perceiver
  39. Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition
  40. Exploiting Low-level Representations for Ultra-Fast Road Segmentation
  41. DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
  42. Factuality of Large Language Models: A Survey
  43. eXplainable Bayesian Multi-Perspective Generative Retrieval
  44. Navigate Biopsy with Ultrasound under Augmented Reality Device: Towards Higher System Performance
  45. Physics-Inspired Degradation Models for Hyperspectral Image Fusion
  46. GLaPE: Gold Label-agnostic Prompt Evaluation and Optimization for Large Language Model
  47. Defining Neural Network Architecture through Polytope Structures of Dataset
  48. Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios
  49. AI-Generated Content Enhanced Computer-Aided Diagnosis Model for Thyroid Nodules: A ChatGPT-Style Assistant
  50. FreDF: Learning to Forecast in the Frequency Domain
  51. Multiplexed all-optical permutation operations using a reconfigurable diffractive optical network
  52. A fast and gridless ORKA algorithm for tracking moving and deforming objects
  53. DeLLMa: Decision Making Under Uncertainty with Large Language Models
  54. KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion
  55. Brain-Body-Task Co-Adaptation can Improve Autonomous Learning and Speed of Bipedal Walking
  56. A Survey on Robotics with Foundation Models: toward Embodied AI
  57. Revisiting the Power of Prompt for Visual Tuning
  58. Empowering Computing and Networks Convergence System with Distributed Cooperative Routing
  59. Evaluating Large Language Models in Analysing Classroom Dialogue
  60. Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction
  61. NOAH: Learning Pairwise Object Category Attentions for Image Classification
  62. AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  63. M3Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing
  64. Timer: Generative Pre-trained Transformers Are Large Time Series Models
  65. Exploring Intrinsic Properties of Medical Images for Self-Supervised Binary Semantic Segmentation
  66. Transolver: A Fast Transformer Solver for PDEs on General Geometries
  67. Loss Landscape Degeneracy and Stagewise Development in Transformers
  68. Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE
  69. Pruner: A Draft-then-Verify Exploration Mechanism to Accelerate Tensor Program Tuning
  70. Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates
  71. Multi-modal Causal Structure Learning and Root Cause Analysis
  72. Decentralized Sum-of-Nonconvex Optimization
  73. Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
  74. A Paradigm for Potential Model Performance Improvement in Classification and Regression Problems. A Proof of Concept
  75. Region-Based Representations Revisited
  76. 3D Lymphoma Segmentation on PET/CT Images via Multi-Scale Information Fusion with Cross-Attention
  77. Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
  78. Stereographic Spherical Sliced Wasserstein Distances
  79. MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
  80. Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
  81. Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation
  82. NetLLM: Adapting Large Language Models for Networking
  83. Video Editing for Video Retrieval
  84. Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning
  85. Copyright Protection in Generative AI: A Technical Perspective
  86. Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals
  87. Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut
  88. Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
  89. Momentum Does Not Reduce Stochastic Noise in Stochastic Gradient Descent
  90. Dynamic Incremental Optimization for Best Subset Selection
  91. Active Learning for Graphs with Noisy Structures
  92. Spin: An Efficient Secure Computation Framework with GPU Acceleration
  93. Diversity Measurement and Subset Selection for Instruction Tuning Datasets
  94. A Survey of Large Language Models in Finance (FinLLMs)
  95. Selecting Large Language Model to Fine-tune via Rectified Scaling Law
  96. CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization
  97. A flexible Bayesian g-formula for causal survival analyses with time-dependent confounding
  98. Efficient Numerical Wave Propagation Enhanced By An End-to-End Deep Learning Model