mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 20 Nov 2022

135 papers

  1. Leveraging per Image-Token Consistency for Vision-Language Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. Diffusion Model Based Posterior Sampling for Noisy Linear Inverse ProblemsDiffusion models → Inverse problems and image restoration
  3. Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing FlowsOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  4. Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch SizeOffline RL and imitation learning from data → Offline RL algorithms
  5. MagicVideo: Efficient Video Generation With Latent Diffusion ModelsDiffusion models → Video generation
  6. Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer EncodersKnowledge distillation → Knowledge distillation for LLMs
  7. Synthesizing Coherent Story with Auto-Regressive Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  8. Scalable Collaborative Learning via Representation SharingKnowledge distillation → Federated, robust and private distillation
  9. AI-KD: Adversarial learning and Implicit regularization for self-Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
  10. IC3D: Image-Conditioned 3D Diffusion for Shape GenerationDiffusion models → 3D, point cloud and scene generation
  11. Joint Embedding Predictive Architectures Focus on Slow FeaturesWorld models → Latent predictive world models
  12. Quadratically Regularized Optimal Transport: nearly optimal potentials and convergence of discrete Laplace operators
  13. The Stack: 3 TB of permissively licensed source code
  14. Progressively Dual Prior Guided Few-shot Semantic Segmentation
  15. Graceful Forgetting II. Data as a Process
  16. FAF: A novel multimodal emotion recognition approach integrating face, body and text
  17. Karyotype AI for Precision Oncology
  18. Automating Rigid Origami Design
  19. A CNN-Transformer Deep Learning Model for Real-time Sleep Stage Classification in an Energy-Constrained Wireless Device
  20. Detecting Conspiracy Theory Against COVID-19 Vaccines
  21. Petroleum prices prediction using data mining techniques -- A Review
  22. An Algorithm for Routing Vectors in Sequences
  23. SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels
  24. RHCO: A Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning for Large-scale Graphs
  25. Counterfactual Learning with Multioutput Deep Kernels
  26. Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation
  27. Graph-based Semi-supervised Local Clustering with Few Labeled Nodes
  28. Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
  29. The Past Does Matter: Correlation of Subsequent States in Trajectory Predictions of Gaussian Process Models
  30. VER: Unifying Verbalizing Entities and Relations
  31. Conceptor-Aided Debiasing of Large Language Models
  32. An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
  33. R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition
  34. DynIBaR: Neural Dynamic Image-Based Rendering
  35. A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
  36. Unifying Tracking and Image-Video Object Detection
  37. Frozen Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks
  38. Learning Nonlinear Couplings in Network of Agents from a Single Sample Trajectory
  39. Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation
  40. Patch-level Gaze Distribution Prediction for Gaze Following
  41. Deep learning delay coordinate dynamics for chaotic attractors from partial observable data
  42. Simultaneously Learning Robust Audio Embeddings and balanced Hash codes for Query-by-Example
  43. Coarse-to-fine Task-driven Inpainting for Geoscience Images
  44. Convolutional Filtering on Sampled Manifolds
  45. Semantic Similarity-Based Clustering of Findings From Security Testing Tools
  46. Safe Control Under Input Limits with Neural Control Barrier Functions
  47. Convexifying Transformers: Improving optimization and understanding of transformer networks
  48. Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues
  49. Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning
  50. Pragmatic Constraint on Distributional Semantics
  51. PointResNet: Residual Network for 3D Point Cloud Segmentation and Classification
  52. Deep Composite Face Image Attacks: Generation, Vulnerability and Detection
  53. Heterogenous Ensemble of Models for Molecular Property Prediction
  54. On the Complexity of Bayesian Generalization
  55. Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  56. Adversarial Cheap Talk
  57. Algorithmic Decision-Making Safeguarded by Human Knowledge
  58. Safe Reinforcement Learning using Data-Driven Predictive Control
  59. Self-supervised iRegNet for the Registration of Longitudinal Brain MRI of Diffuse Glioma Patients
  60. Machine Learning Methods for Anomaly Detection in Nuclear Power Plant Power Transformers
  61. Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric
  62. Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation
  63. Unadjusted Hamiltonian MCMC with Stratified Monte Carlo Time Integration
  64. F2SD: A dataset for end-to-end group detection algorithms
  65. LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders
  66. Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledge
  67. MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection
  68. Distinctive Self-Similar Object Detection
  69. DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion
  70. How to Describe Images in a More Funny Way? Towards a Modular Approach to Cross-Modal Sarcasm Generation
  71. Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval
  72. Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach
  73. Finding active galactic nuclei through Fink
  74. UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning
  75. DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus
  76. Real-time Local Feature with Global Visual Information Enhancement
  77. Federated deep transfer learning for EEG decoding using multiple BCI tasks
  78. A Comparative Analysis of Transfer Learning-based Techniques for the Classification of Melanocytic Nevi
  79. Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression
  80. Font Representation Learning via Paired-glyph Matching
  81. Decoding Attention from Gaze: A Benchmark Dataset and End-to-End Models
  82. A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective
  83. CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion
  84. Efficient Representations of Object Geometry for Reinforcement Learning of Interactive Grasping Policies
  85. When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method
  86. FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
  87. Normalizing Flows for Human Pose Anomaly Detection
  88. Feature Weaken: Vicinal Data Augmentation for Classification
  89. Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
  90. Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation
  91. Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification
  92. Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation
  93. Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
  94. GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds
  95. Traceable and Authenticable Image Tagging for Fake News Detection
  96. Auto-Focus Contrastive Learning for Image Manipulation Detection
  97. MEESO: A Multi-objective End-to-End Self-Optimized Approach for Automatically Building Deep Learning Models
  98. ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression
  99. ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Sample
  100. Learning from Long-Tailed Noisy Data with Sample Selection and Balanced Loss
All 135
  1. Temporal Knowledge Graph Reasoning with Historical Contrastive Learning
  2. Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
  3. Spectral Adversarial Training for Robust Graph Neural Network
  4. Towards Realistic Out-of-Distribution Detection: A Novel Evaluation Framework for Improving Generalization in OOD Detection
  5. Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
  6. Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis
  7. Multi-scale Digital Twin: Developing a fast and physics-informed surrogate model for groundwater contamination with uncertain climate models
  8. Audio-visual video face hallucination with frequency supervision and cross modality support by speech based lip reading loss
  9. Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
  10. Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
  11. PartCom: Part Composition Learning for 3D Open-Set Recognition
  12. DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics
  13. Artificial Interrogation for Attributing Language Models
  14. Interpretable Scientific Discovery with Symbolic Regression: A Review
  15. MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
  16. SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control
  17. UniMASK: Unified Inference in Sequential Decision Problems
  18. Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation
  19. Estimating Task Completion Times for Network Rollouts using Statistical Models within Partitioning-based Regression Methods
  20. Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
  21. A Blockchain Protocol for Human-in-the-Loop AI
  22. An interpretable imbalanced semi-supervised deep learning framework for improving differential diagnosis of skin diseases
  23. Diffeomorphic Information Neural Estimation
  24. Mulco: Recognizing Chinese Nested Named Entities Through Multiple Scopes
  25. Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learning
  26. Context-Aware Data Augmentation for LIDAR 3D Object Detection
  27. Learning to Generate Image Embeddings with User-level Differential Privacy
  28. Mask Off: Analytic-based Malware Detection By Transfer Learning and Model Personalization
  29. SeDR: Segment Representation Learning for Long Documents Dense Retrieval
  30. Non-reversible Parallel Tempering for Deep Posterior Approximation
  31. Context-aware learning of hierarchies of low-fidelity models for multi-fidelity uncertainty quantification
  32. Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery
  33. Instability in clinical risk stratification models using deep learning
  34. Structure-Enhanced Deep Reinforcement Learning for Optimal Transmission Scheduling
  35. Turning Silver into Gold: Domain Adaptation with Noisy Labels for Wearable Cardio-Respiratory Fitness Prediction