mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 29 Sep 2022

198 papers

  1. Scaling Laws for a Multi-Agent Reinforcement Learning ModelLLM agents and tool use → Reinforcement learning for LLM agents
  2. Tuning of Mixture-of-Experts Mixed-Precision Neural NetworksMixture-of-experts → Efficient MoE training and inference systems
  3. Low-Dose CT Using Denoising Diffusion Probabilistic Model for 20× SpeedupDiffusion models → Medical imaging and segmentation
  4. Zero-shot visual reasoning through probabilistic analogical mappingLLM reasoning → Multimodal reasoning
  5. A Benchmark Comparison of Imitation Learning-based Control Policies for Autonomous RacingOffline RL and imitation learning from data → Imitation and offline RL for driving
  6. REST: REtrieve & Self-Train for generative action recognitionSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  7. DreamFusion: Text-to-3D using 2D DiffusionWorld models → Video-generation world models and simulators +1
  8. Contrastive Unsupervised Learning of World Model with Invariant Causal FeaturesWorld models → Latent dynamics models and model-based RL
  9. Spotlight: Mobile UI Understanding using Vision-Language Models with a FocusMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  10. Human Motion Diffusion ModelDiffusion models → Video generation
  11. DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language ProcessingLLM reasoning → Clinical and biomedical applications
  12. Denoising Diffusion Probabilistic Models for Styled Walking SynthesisDiffusion models → Video generation
  13. Analyzing Diffusion as Serial ReproductionDiffusion models → Diffusion foundations and sampling
  14. DiGress: Discrete Denoising diffusion for graph generationDiffusion models → Flow matching, time series and science
  15. Hyper-Representations as Generative Models: Sampling Unseen Neural Network WeightsKnowledge distillation → General knowledge distillation methods
  16. Creative Painting with Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  17. Diffusion Posterior Sampling for General Noisy Inverse ProblemsDiffusion models → Inverse problems and image restoration
  18. Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical ReasoningLLM reasoning → Mathematical reasoning
  19. Denoising MCMC for Accelerating Diffusion-Based Generative ModelsDiffusion models → Diffusion foundations and sampling
  20. Rectified Flow: A Marginal Preserving Approach to Optimal TransportDiffusion models → Flow matching, time series and science
  21. Offline Reinforcement Learning via High-Fidelity Generative Behavior ModelingOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  22. Label driven Knowledge Distillation for Federated Learning with non-IID DataKnowledge distillation → Federated, robust and private distillation
  23. Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face RecognitionKnowledge distillation → General knowledge distillation methods
  24. Re-Imagen: Retrieval-Augmented Text-to-Image GeneratorRetrieval-augmented generation → Multimodal RAG
  25. A Recommendation Approach based on Similarity-Popularity Models of Complex Networks
  26. PrivMVMF: Privacy-Preserving Multi-View Matrix Factorization for Recommender Systems
  27. Accurate, reliable and interpretable solubility prediction of druglike molecules with attention pooling and Bayesian learning
  28. An Ontology for Defect Detection in Metal Additive Manufacturing
  29. Benchmarking Learning Efficiency in Deep Reservoir Computing
  30. Neural-network solutions to stochastic reaction networks
  31. Predicting CO2 Absorption in Ionic Liquids with Molecular Descriptors and Explainable Graph Neural Networks
  32. quEEGNet: Quantum AI for Biosignal Processing
  33. Deep learning and multi-level featurization of graph representations of microstructural data
  34. A note on the potentials of probabilistic and fuzzy logic
  35. Concepts and Experiments on Psychoanalysis Driven Computing
  36. Toward Trustworthy Neural Program Synthesis
  37. Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification
  38. Anomaly localization for copy detection patterns through print estimations
  39. Towards General-Purpose Representation Learning of Polygonal Geometries
  40. Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments
  41. Spikformer: When Spiking Neural Network Meets Transformer
  42. Accurate Long-term Air Temperature Prediction with a Fusion of Artificial Intelligence and Data Reduction Techniques
  43. Augmentation Backdoors
  44. Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review
  45. Modeling driver's evasive behavior during safety-critical lane changes:Two-dimensional time-to-collision and deep reinforcement learning
  46. Nonconvex Matrix Factorization is Geodesically Convex: Global Landscape Analysis for Fixed-rank Matrix Optimization From a Riemannian Perspective
  47. Understanding Interventional TreeSHAP : How and Why it Works
  48. Heterogeneous reconstruction of deformable atomic models in Cryo-EM
  49. Structured Optimal Variational Inference for Dynamic Latent Space Models
  50. Quantifying Harm
  51. ConceptNet infused DialoGPT for Underlying Commonsense Understanding and Reasoning in Dialogue Response Generation
  52. How to tackle an emerging topic? Combining strong and weak labels for Covid news NER
  53. Restricted Strong Convexity of Deep Learning Models with Smooth Activations
  54. OAK4XAI: Model towards Out-Of-Box eXplainable Artificial Intelligence for Digital Agriculture
  55. Improving Molecular Pretraining with Complementary Featurizations
  56. MUG: Interactive Multimodal Grounding on User Interfaces
  57. Likelihood Adjusted Semidefinite Programs for Clustering Heterogeneous Data
  58. AICCA: AI-driven Cloud Classification Atlas
  59. Open-source tool for Airway Segmentation in Computed Tomography using 2.5D Modified EfficientDet: Contribution to the ATM22 Challenge
  60. Unpacking Large Language Models with Conceptual Consistency
  61. Improving Generative Flow Networks with Path Regularization
  62. Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
  63. Automatic satellite building construction monitoring
  64. Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning
  65. 3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
  66. Partially calibrated semi-generalized pose from hybrid point correspondences
  67. Few-shot Text Classification with Dual Contrastive Consistency
  68. Reasoning about Complex Networks: A Logic Programming Approach
  69. Provably expressive temporal graph networks
  70. Graph Attention Network for Camera Relocalization on Dynamic Scenes
  71. Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
  72. Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes
  73. Generalizability of Adversarial Robustness Under Distribution Shifts
  74. Large-Scale Spatial Cross-Calibration of Hinode/SOT-SP and SDO/HMI
  75. Guided Unsupervised Learning by Subaperture Decomposition for Ocean SAR Image Retrieval
  76. Automatic Data Augmentation via Invariance-Constrained Learning
  77. Understanding Collapse in Non-Contrastive Siamese Representation Learning
  78. Effective Vision Transformer Training: A Data-Centric Perspective
  79. Compositional Semantic Parsing with Large Language Models
  80. Dilated Neighborhood Attention Transformer
  81. Optimistic MLE -- A Generic Model-based Algorithm for Partially Observable Sequential Decision Making
  82. Multiple Modes for Continual Learning
  83. Machine learning and invariant theory
  84. Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
  85. No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy"
  86. Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging
  87. Enumeration of max-pooling responses with generalized permutohedra
  88. Transformer Meets Boundary Value Inverse Problems
  89. Causal Inference via Nonlinear Variable Decorrelation for Healthcare Applications
  90. Statistical Learning and Inverse Problems: A Stochastic Gradient Approach
  91. DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment
  92. Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals
  93. EiHi Net: Out-of-Distribution Generalization Paradigm
  94. EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
  95. Reinforcement Learning Algorithms: An Overview and Classification
  96. NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer
  97. Does Zero-Shot Reinforcement Learning Exist?
  98. Training Normalizing Flows from Dependent Data
  99. Graph Anomaly Detection with Graph Neural Networks: Current Status and Challenges
  100. Domain-Unified Prompt Representations for Source-Free Domain Generalization
All 198
  1. Chandojnanam: A Sanskrit Meter Identification and Utilization System
  2. GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions
  3. Spiking Neural Networks for event-based action recognition: A new task to understand their advantage
  4. Graph Modeling in Computer Assisted Automotive Development
  5. Patients' Severity States Classification based on Electronic Health Record (EHR) Data using Multiple Machine Learning and Deep Learning Approaches
  6. Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
  7. Joint Optimization of Energy Consumption and Completion Time in Federated Learning
  8. Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing
  9. Mask-Guided Image Person Removal with Data Synthesis
  10. Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
  11. Joint Embedding Self-Supervised Learning in the Kernel Regime
  12. Sequential Attention for Feature Selection
  13. Repairing Bugs in Python Assignments Using Large Language Models
  14. Accelerating Laboratory Automation Through Robot Skill Learning For Sample Scraping
  15. ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition
  16. Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
  17. Bridging the Gap to Real-World Object-Centric Learning
  18. 4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation
  19. Continuous PDE Dynamics Forecasting with Implicit Neural Representations
  20. TERMinator: A system for scientific texts processing
  21. META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions
  22. Meta Knowledge Condensation for Federated Learning
  23. Federated Stain Normalization for Computational Pathology
  24. Access Control with Encrypted Feature Maps for Object Detection Models
  25. Lightweight Monocular Depth Estimation with an Edge Guided Network
  26. On the Convergence of AdaGrad(Norm) on Rd: Beyond Convexity, Non-Asymptotic Rate and Acceleration
  27. Towards Lightweight Black-Box Attacks against Deep Neural Networks
  28. Trading off Quality for Efficiency of Community Detection: An Inductive Method across Graphs
  29. SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis
  30. Named Entity Recognition in Industrial Tables using Tabular Language Models
  31. polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics
  32. Make-A-Video: Text-to-Video Generation without Text-Video Data
  33. Sparse PCA With Multiple Components
  34. Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder
  35. A case study of spatiotemporal forecasting techniques for weather forecasting
  36. Learning Parsimonious Dynamics for Generalization in Reinforcement Learning
  37. Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition
  38. Batch Normalization Explained
  39. RECALL: Rehearsal-free Continual Learning for Object Classification
  40. R2C-GAN: Restore-to-Classify Generative Adversarial Networks for Blind X-Ray Restoration and COVID-19 Classification
  41. Model Zoos: A Dataset of Diverse Populations of Neural Network Models
  42. Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain
  43. A Multiagent Framework for the Asynchronous and Collaborative Extension of Multitask ML Systems
  44. Dataset Complexity Assessment Based on Cumulative Maximum Scaled Area Under Laplacian Spectrum
  45. Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
  46. FastPacket: Towards Pre-trained Packets Embedding based on FastText for next-generation NIDS
  47. In Search of Projectively Equivariant Networks
  48. TruEyes: Utilizing Microtasks in Mobile Apps for Crowdsourced Labeling of Machine Learning Datasets
  49. Facial Landmark Predictions with Applications to Metaverse
  50. GROOT: Corrective Reward Optimization for Generative Sequential Labeling
  51. Digital and Physical Face Attacks: Reviewing and One Step Further
  52. Prompt-guided Scene Generation for 3D Zero-Shot Learning
  53. A canonical correlation-based framework for performance analysis of radio access networks
  54. Towards Equalised Odds as Fairness Metric in Academic Performance Prediction
  55. Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis
  56. Causal inference in drug discovery and development
  57. Correlated Feature Aggregation by Region Helps Distinguish Aggressive from Indolent Clear Cell Renal Cell Carcinoma Subtypes on CT
  58. Bounded Future MS-TCN++ for surgical gesture recognition
  59. Increasing Model Generalizability for Unsupervised Domain Adaptation
  60. A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection
  61. Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing
  62. An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
  63. Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning
  64. COMPILING: A Benchmark Dataset for Chinese Complexity Controllable Definition Generation
  65. Fair admission risk prediction with proportional multicalibration
  66. Dataset Distillation Using Parameter Pruning
  67. Spherical Image Inpainting with Frame Transformation and Data-driven Prior Deep Networks
  68. Dataset Distillation for Medical Dataset Sharing
  69. Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings
  70. Online pseudo labeling for polyp segmentation with momentum networks
  71. Dynamic Surrogate Switching: Sample-Efficient Search for Factorization Machine Configurations in Online Recommendations
  72. Bayesian Neural Network Versus Ex-Post Calibration For Prediction Uncertainty
  73. PerSign: Personalized Bangladeshi Sign Letters Synthesis
  74. Spatial Moment Pooling Improves Neural Image Assessment
  75. Correcting the Sub-optimal Bit Allocation
  76. COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization
  77. Local and Regional Counterfactual Rules: Summarized and Robust Recourses
  78. Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation
  79. Computational Complexity of Sub-Linear Convergent Algorithms
  80. Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts
  81. Regularizing Neural Network Training via Identity-wise Discriminative Feature Suppression
  82. A Secure Federated Learning Framework for Residential Short Term Load Forecasting
  83. NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction
  84. Convergence of the mini-batch SIHT algorithm
  85. Feature Selection via the Intervened Interpolative Decomposition and its Application in Diversifying Quantitative Strategies
  86. Low-Stabilizer-Complexity Quantum States Are Not Pseudorandom
  87. Motion and Appearance Adaptation for Cross-Domain Motion Transfer
  88. Self-Configurable Stabilized Real-Time Detection Learning for Autonomous Driving Applications
  89. How Powerful is Implicit Denoising in Graph Neural Networks
  90. How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?
  91. A Two-Stage Method for Chinese AMR Parsing
  92. On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks
  93. Bidirectional Language Models Are Also Few-shot Learners
  94. NVRadarNet: Real-Time Radar Obstacle and Free Space Detection for Autonomous Driving
  95. Multi-stage Information Retrieval for Vietnamese Legal Texts
  96. Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training
  97. Semantics-Guided Object Removal for Facial Images: with Broad Applicability and Robust Style Preservation
  98. Intrinsic Dimensionality Estimation within Tight Localities: A Theoretical and Experimental Analysis