mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 9 Mar 2023

216 papers

  1. Learning the Wrong Lessons: Inserting Trojans During Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
  2. Weakly-Supervised HOI Detection from Interaction Labels Only and Language/Vision-Language PriorsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  3. Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-TuningOffline RL and imitation learning from data → Offline RL algorithms
  4. Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  5. 3DGen: Triplane Latent Diffusion for Textured Mesh GenerationDiffusion models → 3D, point cloud and scene generation
  6. Rethinking Range View Representation for LiDAR SegmentationWorld models → World modeling from LiDAR generation
  7. Natural scene reconstruction from fMRI signals using generative latent diffusionDiffusion models → Medical imaging and segmentation
  8. Refined Vision-Language Modeling for Fine-grained Multi-modal Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  9. Detecting Images Generated by DiffusersDiffusion models → Image generation, text-to-image and editing
  10. Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object DetectionLLM reasoning → Multimodal reasoning
  11. hierarchical network with decoupled knowledge distillation for speech emotion recognitionKnowledge distillation → Multimodal distillation
  12. Cones: Concept Neurons in Diffusion Models for Customized GenerationDiffusion models → Image generation, text-to-image and editing
  13. MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance SegmentationDiffusion models → Medical imaging and segmentation
  14. Task Aware Dreamer for Task Generalization in Reinforcement LearningWorld models → Latent dynamics models and model-based RL
  15. Learn More for Food Recognition via Progressive Self-DistillationKnowledge distillation → General knowledge distillation methods
  16. Unifying Layout Generation with a Decoupled Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  17. Smooth and Stepwise Self-Distillation for Object DetectionKnowledge distillation → Detection and dense prediction distillation
  18. ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark
  19. Machine learning tools to improve nonlinear modeling parameters of RC columns
  20. Automated visual inspection of CMS HGCAL silicon sensor surface using an ensemble of a deep convolutional autoencoder and classifier
  21. Probability-based Global Cross-modal Upsampling for Pansharpening
  22. Enhancing Peak Network Traffic Prediction via Time-Series Decomposition
  23. Evolving Populations of Diverse RL Agents with MAP-Elites
  24. Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning
  25. Optimizing CAD Models with Latent Space Manipulation
  26. Visualizing Semiotics in Generative Adversarial Networks
  27. A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning
  28. Comparison of Probabilistic Deep Learning Methods for Autism Detection
  29. AptSim2Real: Approximately-Paired Sim-to-Real Image Translation
  30. Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning
  31. Fitting Low-rank Models on Egocentrically Sampled Partial Networks
  32. Types of Approaches, Applications and Challenges in the Development of Sentiment Analysis Systems
  33. Text-to-ECG: 12-Lead Electrocardiogram Synthesis conditioned on Clinical Text Reports
  34. Stock Trend Prediction: A Semantic Segmentation Approach
  35. Multi-task Meta Label Correction for Time Series Prediction
  36. TQ-Net: Mixed Contrastive Representation Learning For Heterogeneous Test Questions
  37. Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code
  38. Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification
  39. Provably Convergent Plug-and-Play Quasi-Newton Methods
  40. On the Robustness of Text Vectorizers
  41. BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spaces
  42. NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks
  43. Analysis and Evaluation of Explainable Artificial Intelligence on Suicide Risk Assessment
  44. Depression Diagnosis and Drug Response Prediction via Recurrent Neural Networks and Transformers Utilizing EEG Signals
  45. Hierarchical Neural Program Synthesis
  46. Probe: Learning Users' Personalized Projection Bias in Intertemporal Choices
  47. Variational formulations of ODE-Net as a mean-field optimal control problem and existence results
  48. Convolutional Cross-View Pose Estimation
  49. On the Value of Stochastic Side Information in Online Learning
  50. Explainable Goal Recognition: A Framework Based on Weight of Evidence
  51. CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation
  52. KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input
  53. An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximation
  54. Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards
  55. SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces
  56. Generalization analysis of an unfolding network for analysis-based Compressed Sensing
  57. Open World Classification with Adaptive Negative Samples
  58. Evaluating the Robustness of Conversational Recommender Systems by Adversarial Examples
  59. Exploration of the search space of Gaussian graphical models for paired data
  60. Optimal active particle navigation meets machine learning
  61. An Evaluation of Non-Contrastive Self-Supervised Learning for Federated Medical Image Analysis
  62. EfficientTempNet: Temporal Super-Resolution of Radar Rainfall
  63. Position Paper on Dataset Engineering to Accelerate Science
  64. Computably Continuous Reinforcement-Learning Objectives are PAC-learnable
  65. On the Soundness of XAI in Prognostics and Health Management (PHM)
  66. A Lite Fireworks Algorithm with Fractal Dimension Constraint for Feature Selection
  67. PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
  68. Scaling up GANs for Text-to-Image Synthesis
  69. Planning with Large Language Models for Code Generation
  70. TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
  71. Computable Phenotypes to Characterize Changing Patient Brain Dysfunction in the Intensive Care Unit
  72. Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision
  73. PDSketch: Integrated Planning Domain Programming and Learning
  74. Users are the North Star for AI Transparency
  75. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
  76. Mark My Words: Dangers of Watermarked Images in ImageNet
  77. Learning Stationary Markov Processes with Contrastive Adjustment
  78. Sparse and Local Networks for Hypergraph Reasoning
  79. On the Expressiveness and Generalization of Hypergraph Neural Networks
  80. Learning Rational Subgoals from Demonstrations and Instructions
  81. Efficient Testable Learning of Halfspaces with Adversarial Label Noise
  82. Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking
  83. Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases
  84. Resolving quantitative MRI model degeneracy with machine learning via training data distribution design
  85. Understanding the Challenges and Opportunities of Pose-based Anomaly Detection
  86. Presentation Attack Detection with Advanced CNN Models for Noncontact-based Fingerprint Systems
  87. Beware of Instantaneous Dependence in Reinforcement Learning
  88. Power and Interference Control for VLC-Based UDN: A Reinforcement Learning Approach
  89. Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks
  90. Quantum Splines for Non-Linear Approximations
  91. Kernel Regression with Infinite-Width Neural Networks on Millions of Examples
  92. FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning
  93. Fast kernel methods for Data Quality Monitoring as a goodness-of-fit test
  94. Deep Functional Predictive Control for Strawberry Cluster Manipulation using Tactile Prediction
  95. Greener yet Powerful: Taming Large Code Generation Models with Quantization
  96. PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
  97. Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation
  98. Data-dependent Generalization Bounds via Variable-Size Compressibility
  99. Proceedings 11th International Workshop on Theorem Proving Components for Educational Software
  100. Seeing ChatGPT Through Students' Eyes: An Analysis of TikTok Data
All 216
  1. Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective
  2. Knowledge-augmented Few-shot Visual Relation Detection
  3. Penalized Deep Partially Linear Cox Models with Application to CT Scans of Lung Cancer Patients
  4. Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift
  5. Cloudless-Training: A Framework to Improve Efficiency of Geo-Distributed ML Training
  6. Tucker Bilinear Attention Network for Multi-scale Remote Sensing Object Detection
  7. BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset
  8. Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE
  9. WASD: A Wilder Active Speaker Detection Dataset
  10. 3D Video Loops from Asynchronous Input
  11. MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition
  12. SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimation
  13. Learning Strategic Value and Cooperation in Multi-Player Stochastic Games through Side Payments
  14. National-scale 1-m resolution land-cover mapping for the entire China based on a low-cost solution and open-access data
  15. M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities
  16. CoolPINNs: A Physics-informed Neural Network Modeling of Active Cooling in Vascular Systems
  17. Perspective Projection-Based 3D CT Reconstruction from Biplanar X-rays
  18. Dynamic Stashing Quantization for Efficient Transformer Training
  19. Knowledge-augmented Risk Assessment (KaRA): a hybrid-intelligence framework for supporting knowledge-intensive risk assessment of prospect candidates
  20. Effective Pseudo-Labeling based on Heatmap for Unsupervised Domain Adaptation in Cell Detection
  21. From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
  22. Fast post-process Bayesian inference with Variational Sparse Bayesian Quadrature
  23. Masked Image Modeling with Local Multi-Scale Reconstruction
  24. Efficient Certified Training and Robustness Verification of Neural ODEs
  25. Probabilistic 3d regression with projected huber distribution
  26. Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation
  27. GPGait: Generalized Pose-based Gait Recognition
  28. Structure-Aware Group Discrimination with Adaptive-View Graph Encoder: A Fast Graph Contrastive Learning Framework
  29. Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images
  30. SEAM: An Integrated Activation-Coupled Model of Sentence Processing and Eye Movements in Reading
  31. Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow
  32. Geometry of Language
  33. FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learning
  34. Real-time scheduling of renewable power systems through planning-based reinforcement learning
  35. RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving
  36. Mastering Strategy Card Game (Hearthstone) with Improved Techniques
  37. Revisiting Rotation Averaging: Uncertainties and Robust Losses
  38. Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation
  39. GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning
  40. Virtual Inverse Perspective Mapping for Simultaneous Pose and Motion Estimation
  41. A Framework for History-Aware Hyperparameter Optimisation in Reinforcement Learning
  42. Blind2Sound: Self-Supervised Image Denoising without Residual Noise
  43. Classification in Histopathology: A unique deep embeddings extractor for multiple classification tasks
  44. RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
  45. Reconstructing the Hubble parameter with future Gravitational Wave missions using Machine Learning
  46. TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering
  47. Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation
  48. EVOLIN Benchmark: Evaluation of Line Detection and Association
  49. Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation
  50. π-augmented pregroups and applications to linguistics
  51. Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution
  52. Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts
  53. 3D wind field profiles from hyperspectral sounders: revisiting optic-flow from a meteorological perspective
  54. Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?
  55. Provable Data Subset Selection For Efficient Neural Network Training
  56. ESCL: Equivariant Self-Contrastive Learning for Sentence Representations
  57. The joint node degree distribution in the ErdHos-R'enyi network
  58. Blind deblurring of hyperspectral document images
  59. Hybrid Dual Mean-Teacher Network With Double-Uncertainty Guidance for Semi-Supervised Segmentation of MRI Scans
  60. Dominating Set Database Selection for Visual Place Recognition
  61. M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
  62. Entropic Wasserstein Component Analysis
  63. SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
  64. Multi-level Memory-augmented Appearance-Motion Correspondence Framework for Video Anomaly Detection
  65. Segmentation method for cerebral blood vessels from MRA using hysteresis
  66. Synthetic Pseudo Anomalies for Unsupervised Video Anomaly Detection: A Simple yet Efficient Framework based on Masked Autoencoder
  67. Retinal Image Segmentation with Small Datasets
  68. Updated version: A Video Anomaly Detection Framework based on Appearance-Motion Semantics Representation Consistency
  69. StyleDiff: Attribute Comparison Between Unlabeled Datasets in Latent Disentangled Space
  70. Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics
  71. Optimizing Sparse Linear Algebra Through Automatic Format Selection and Machine Learning
  72. Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting
  73. Improving Video Retrieval by Adaptive Margin
  74. Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction
  75. Revisiting the relevance of traditional genres: a network analysis of fiction readers' preferences
  76. DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
  77. Efficient Transformer-based 3D Object Detection with Dynamic Token Halting
  78. Learning the Legibility of Visual Text Perturbations
  79. Pedestrian Attribute Editing for Gait Recognition and Anonymization
  80. Identification of Systematic Errors of Image Classifiers on Rare Subgroups
  81. MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors
  82. Conceptual Reinforcement Learning for Language-Conditioned Tasks
  83. Toward Unsupervised Realistic Visual Question Answering
  84. Distortion-Disentangled Contrastive Learning
  85. ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction
  86. Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
  87. Semi-Federated Learning for Collaborative Intelligence in Massive IoT Networks
  88. Diversity-Measurable Anomaly Detection
  89. Unsupervised Language agnostic WER Standardization
  90. Invertible Kernel PCA with Random Fourier Features
  91. Exploiting Contextual Structure to Generate Useful Auxiliary Tasks
  92. Gauges and Accelerated Optimization over Smooth and/or Strongly Convex Sets
  93. Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning
  94. Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
  95. Out-of-distribution Detection with Implicit Outlier Transformation
  96. CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing
  97. SSL^2: Self-Supervised Learning meets Semi-Supervised Learning: Multiple Sclerosis Segmentation in 7T-MRI from large-scale 3T-MRI
  98. Phase transition for detecting a small community in a large network
  99. X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion
  100. DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
  101. Improved Regret Bounds for Online Kernel Selection under Bandit Feedback
  102. Towards Robust Image-in-Audio Deep Steganography
  103. Learning Representation for Anomaly Detection of Vehicle Trajectories
  104. Rethinking Visual Prompt Learning as Masked Visual Token Modeling
  105. Optimization-Based Eye Tracking using Deflectometric Information
  106. Text-Visual Prompting for Efficient 2D Temporal Video Grounding
  107. Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation
  108. ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
  109. The Robustness Verification of Linear Sound Quantum Classifiers
  110. Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient Estimation
  111. Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo
  112. LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
  113. Reconstruction of Cardiac Cine MRI Using Motion-Guided Deformable Alignment and Multi-Resolution Fusion
  114. NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging
  115. Time-Dependent Blackwell Approachability and Application to Absorbing Games
  116. Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize