mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 29 Nov 2022

245 papers

  1. Exploiting Category Names for Few-Shot Classification with Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  2. Offline Policy Evaluation and Optimization under ConfoundingOffline RL and imitation learning from data → Offline RL algorithms
  3. SinDDM: A Single Image Denoising Diffusion ModelDiffusion models → Diffusion foundations and sampling
  4. Improving Commonsense in Vision-Language Models via Knowledge Graph RiddlesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  5. Abstract Visual Reasoning with Tangram ShapesLLM reasoning → Multimodal reasoning
  6. DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelsDiffusion models → 3D, point cloud and scene generation
  7. NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg ViewsDiffusion models → 3D, point cloud and scene generation
  8. DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative ModelDiffusion models → 3D, point cloud and scene generation
  9. Learning and Understanding a Disentangled Feature Representation for Hidden Parameters in Reinforcement LearningWorld models → Latent dynamics models and model-based RL
  10. Curriculum Temperature for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  11. Wavelet Diffusion Models are fast and scalable Image GeneratorsDiffusion models → Diffusion foundations and sampling
  12. Unsupervised Visual Defect Detection with Score-Based Generative ModelDiffusion models → Flow matching, time series and science
  13. Behavior Estimation from Multi-Source Data for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  14. Dimensionality-Varying Diffusion ProcessDiffusion models → Diffusion foundations and sampling
  15. Offline Reinforcement Learning with Closed-Form Policy Improvement OperatorsOffline RL and imitation learning from data → Offline RL algorithms
  16. Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-ResolutionKnowledge distillation → General knowledge distillation methods
  17. The Effectiveness of World Models for Continual Reinforcement LearningWorld models → Latent dynamics models and model-based RL
  18. Discrete Control in Real-World Driving Environments using Deep Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving
  19. Similarity Distribution based Membership Inference Attack on Person Re-identificationLLM safety and security → Membership inference attacks
  20. Data Poisoning Attack Aiming the Vulnerability of Continual LearningLLM safety and security → Backdoor and data poisoning attacks
  21. Peano: Learning Formal Mathematical ReasoningLLM reasoning → Mathematical reasoning
  22. MegaBlocks: Efficient Sparse Training with Mixture-of-ExpertsMixture-of-experts → Efficient MoE training and inference systems
  23. Zero-Shot Learning for Joint Intent and Slot Labeling
  24. Improving astroBERT using Semantic Textual Similarity
  25. Transformer-based Hand Gesture Recognition via High-Density EMG Signals: From Instantaneous Recognition to Fusion of Motor Unit Spike Trains
  26. Reservoir Computing-based Multi-Symbol Equalization for PAM 4 Short-reach Transmission
  27. Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling
  28. MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition
  29. Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time
  30. Autotuning PID control using Actor-Critic Deep Reinforcement Learning
  31. Airfoil Shape Optimization using Deep Q-Network
  32. Automated Play-Testing Through RL Based Human-Like Play-Styles Generation
  33. Time-shift selection for reservoir computing using a rank-revealing QR algorithm
  34. Better Transcription of UK Supreme Court Hearings
  35. SparsePose: Sparse-View Camera Pose Regression and Refinement
  36. Wearing the Same Outfit in Different Ways -- A Controllable Virtual Try-on Method
  37. QuadFormer: Quadruple Transformer for Unsupervised Domain Adaptation in Power Line Segmentation of Aerial Images
  38. A Geometric Model for Polarization Imaging on Projective Cameras
  39. Infinite-width limit of deep linear neural networks
  40. SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers
  41. Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics
  42. Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification
  43. DINER: Depth-aware Image-based NEural Radiance fields
  44. Identification of the Breach of Short-term Rental Regulations in Irish Rent Pressure Zones
  45. Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer
  46. Top-Down Synthesis for Library Learning
  47. Towards Dynamic Causal Discovery with Rare Events: A Nonparametric Conditional Independence Test
  48. ButterflyNet2D: Bridging Classical Methods and Neural Network Methods in Image Processing
  49. Brain Tumor MRI Classification using a Novel Deep Residual and Regional CNN
  50. Performance Evaluation of Vanilla, Residual, and Dense 2D U-Net Architectures for Skull Stripping of Augmented 3D T1-weighted MRI Head Scans
  51. Relative Sparsity for Medical Decision Problems
  52. Testing GLOM's ability to infer wholes from ambiguous parts
  53. Transfer Learning with Uncertainty Quantification: Random Effect Calibration of Source to Target (RECaST)
  54. Simple and Scalable Algorithms for Cluster-Aware Precision Medicine
  55. Numerical evidence against advantage with quantum fidelity kernels on classical data
  56. Soft Alignment Objectives for Robust Adaptation of Language Generation
  57. Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Support
  58. Multimodal Learning for Multi-Omics: A Survey
  59. Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing
  60. TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages
  61. Graph Neural Networks: A Powerful and Versatile Tool for Advancing Design, Reliability, and Security of ICs
  62. On the Ability of Graph Neural Networks to Model Interactions Between Vertices
  63. Coder Reviewer Reranking for Code Generation
  64. Taming Normalizing Flows
  65. AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials
  66. Chaining Simultaneous Thoughts for Numerical Reasoning
  67. Linear-Time Algorithms for Front-Door Adjustment in Causal Graphs
  68. Linear Causal Disentanglement via Interventions
  69. Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation
  70. Will My Robot Achieve My Goals? Predicting the Probability that an MDP Policy Reaches a User-Specified Behavior Target
  71. A Revenue Function for Comparison-Based Hierarchical Clustering
  72. Estimating the minimizer and the minimum value of a regression function under passive design
  73. Holding AI to Account: Challenges for the Delivery of Trustworthy AI in Healthcare
  74. Synthetic data enable experiments in atomistic machine learning
  75. Exploring the Long-Term Generalization of Counting Behavior in RNNs
  76. Multi-agent reinforcement learning for wall modeling in LES of flow over periodic hills
  77. RGB no more: Minimally-decoded JPEG Vision Transformers
  78. Parameterisation of Reasoning on Temporal Markov Logic Networks
  79. Procedural Image Programs for Representation Learning
  80. Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges
  81. Bayesian Simultaneous Factorization and Prediction Using Multi-Omic Data
  82. Self-Supervised Mental Disorder Classifiers via Time Reversal
  83. Bayesian Semiparametric Model for Sequential Treatment Decisions with Informative Timing
  84. Compressing Volumetric Radiance Fields to 1 MB
  85. Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
  86. Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations
  87. Reusable Self-Attention-based Recommender System for Fashion
  88. POLCOVID: a multicenter multiclass chest X-ray database (Poland, 2020-2021)
  89. Real-time Blind Deblurring Based on Lightweight Deep-Wiener-Network
  90. Outfit Generation and Recommendation -- An Experimental Study
  91. BARTSmiles: Generative Masked Language Models for Molecular Representations
  92. Fourier-Net: Fast Image Registration with Band-limited Deformation
  93. Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributions
  94. On the Power of Foundation Models
  95. TF-Net: Deep Learning Empowered Tiny Feature Network for Night-time UAV Detection
  96. A3T: Accuracy Aware Adversarial Training
  97. Approximating Intersections and Differences Between Linear Statistical Shape Models Using Markov Chain Monte Carlo
  98. PLA: Language-Driven Open-Vocabulary 3D Scene Understanding
  99. A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations
  100. Controllable speech synthesis by learning discrete phoneme-level prosodic representations
All 245
  1. Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
  2. Transferability Estimation Based On Principal Gradient Expectation
  3. Double Robust Bayesian Inference on Average Treatment Effects
  4. LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation
  5. Lightweight Structure-Aware Attention for Visual Understanding
  6. Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches
  7. Common Knowledge of Abstract Groups
  8. Differentiable User Models
  9. A survey on multi-player bandits
  10. NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration
  11. Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation
  12. Learning to Optimize with Dynamic Mode Decomposition
  13. PatchMatch-Stereo-Panorama, a fast dense reconstruction from 360deg video images
  14. Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning
  15. Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text Corpora
  16. Advancing Deep Metric Learning Through Multiple Batch Norms And Multi-Targeted Adversarial Examples
  17. Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion
  18. Causal Inference with Conditional Instruments using Deep Generative Models
  19. Based on particle swarm optimization support vector machine model of the electric car sales strategy research
  20. A Cross-Conformal Predictor for Multi-label Classification
  21. Closing the gap between SVRG and TD-SVRG with Gradient Splitting
  22. DCDetector: An IoT terminal vulnerability mining system based on distributed deep ensemble learning under source code representation
  23. SimCS: Simulation for Domain Incremental Online Continual Segmentation
  24. Triadic Temporal Exponential Random Graph Models (TTERGM)
  25. Building Resilience to Out-of-Distribution Visual Data via Input Optimization and Model Finetuning
  26. ReAssigner: A Plug-and-Play Virtual Machine Scheduling Intensifier for Heterogeneous Requests
  27. Configurable Agent With Reward As Input: A Play-Style Continuum Generation
  28. Which Shortcut Solution Do Question Answering Models Prefer to Learn?
  29. Metal-conscious Embedding for CBCT Projection Inpainting
  30. Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learning
  31. AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning
  32. Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation
  33. Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks
  34. Disentangled Generation with Information Bottleneck for Few-Shot Learning
  35. Context-Aware Robust Fine-Tuning
  36. CUNI Submission in WMT22 General Task
  37. Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi
  38. Few-shot Query-Focused Summarization with Prefix-Merging
  39. Scalable Hierarchical Over-the-Air Federated Learning
  40. Artifact Removal in Histopathology Images
  41. Out-Of-Distribution Detection Is Not All You Need
  42. New Results for the Text Recognition of Arabic Maghrib=i Manuscripts -- Managing an Under-resourced Script
  43. Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology
  44. AdaEnlight: Energy-aware Low-light Video Stream Enhancement on Mobile Devices
  45. Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting
  46. G-CMP: Graph-enhanced Contextual Matrix Profile for unsupervised anomaly detection in sensor-based remote health monitoring
  47. Inferring Attack Relations for Gradual Semantics
  48. Machine learning emulation of a local-scale UK climate model
  49. Timing-Based Backpropagation in Spiking Neural Networks Without Single-Spike Restrictions
  50. PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
  51. Encoder-Decoder Model for Suffix Prediction in Predictive Monitoring
  52. Text Representation Enrichment Utilizing Graph based Approaches: Stock Market Technical Analysis Case Study
  53. Dependency-aware Self-training for Entity Alignment
  54. Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks
  55. Better Generalized Few-Shot Learning Even Without Base Data
  56. Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering
  57. Understanding and Enhancing Robustness of Concept-based Models
  58. Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning
  59. ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
  60. Analysis of Training Object Detection Models with Synthetic Data
  61. On Large-Scale Multiple Testing Over Networks: An Asymptotic Approach
  62. NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
  63. Evaluating and reducing the distance between synthetic and real speech distributions
  64. Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Loss
  65. Model Extraction Attack against Self-supervised Speech Models
  66. Linear Complexity Gibbs Sampling for Generalized Labeled Multi-Bernoulli Filtering
  67. AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification
  68. Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning
  69. Learn to See Faster: Pushing the Limits of High-Speed Camera with Deep Underexposed Image Denoising
  70. Syntactic Substitutability as Unsupervised Dependency Syntax
  71. Diverse Multi-Answer Retrieval with Determinantal Point Processes
  72. JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
  73. Novelty Detection for Election Fraud: A Case Study with Agent-Based Simulation Data
  74. Textual Enhanced Contrastive Learning for Solving Math Word Problems
  75. PatchMix Augmentation to Identify Causal Features in Few-shot Learning
  76. UDE: A Unified Driving Engine for Human Motion Generation
  77. Incorporating Multi-armed Bandit with Local Search for MaxSAT
  78. A Charge Domain P-8T SRAM Compute-In-Memory with Low-Cost DAC/ADC Operation for 4-bit Input Processing
  79. Lie Group Forced Variational Integrator Networks for Learning and Control of Robot Systems
  80. Convex Relaxations for Isometric and Equiareal NRSfM
  81. DiffG-RL: Leveraging Difference between State and Common Sense
  82. Asymptotic consistency of the WSINDy algorithm in the limit of continuum data
  83. Impact of Automatic Image Classification and Blind Deconvolution in Improving Text Detection Performance of the CRAFT Algorithm
  84. MedalCare-XL: 16,900 healthy and pathological 12 lead ECGs obtained through electrophysiological simulations
  85. MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
  86. Towards Generalized Open Information Extraction
  87. End-to-End Neural Discourse Deixis Resolution in Dialogue
  88. AirFormer: Predicting Nationwide Air Quality in China with Transformers
  89. One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
  90. Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library
  91. Democratizing Machine Learning for Interdisciplinary Scholars: Report on Organizing the NLP+CSS Online Tutorial Series
  92. Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference
  93. Extending the Subwording Model of Multilingual Pretrained Models for New Languages
  94. Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
  95. FC-PINO: High Precision Physics-Informed Neural Operators via Fourier Continuation
  96. Generalized Face Anti-Spoofing via Multi-Task Learning and One-Side Meta Triplet Loss
  97. Enhanced artificial intelligence-based diagnosis using CBCT with internal denoising: Clinical validation for discrimination of fungal ball, sinusitis, and normal cases in the maxillary sinus
  98. Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
  99. When Quantum Information Technologies Meet Blockchain in Web 3.0
  100. PiggyBack: Pretrained Visual Question Answering Environment for Backing up Non-deep Learning Professionals
  101. Segment-based fusion of multi-sensor multi-scale satellite soil moisture retrievals
  102. Robustness Disparities in Face Detection
  103. Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks
  104. Posterior Sampling for Continuing Environments
  105. Offline Supervised Learning V.S. Online Direct Policy Optimization: A Comparative Study and A Unified Training Paradigm for Neural Network-Based Optimal Feedback Control
  106. Backdoor Vulnerabilities in Normally Trained Deep Learning Models
  107. Compressing Cross-Lingual Multi-Task Models at Qualtrics
  108. Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning
  109. Device Modeling Bias in ReRAM-based Neural Network Simulations
  110. Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT
  111. BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems
  112. Prompted Opinion Summarization with GPT-3.5
  113. Optimizing Stock Option Forecasting with the Assembly of Machine Learning Models and Improved Trading Strategies
  114. Performance Evaluation, Optimization and Dynamic Decision in Blockchain Systems: A Recent Overview
  115. Equivalence Between SE(3) Equivariant Networks via Steerable Kernels and Group Convolution
  116. Multi-robot Social-aware Cooperative Planning in Pedestrian Environments Using Multi-agent Reinforcement Learning
  117. Towards More Robust Interpretation via Local Gradient Alignment
  118. FakeEdge: Alleviate Dataset Shift in Link Prediction
  119. Learning Antidote Data to Individual Unfairness
  120. Composition based oxidation state prediction of materials using deep learning
  121. HashEncoding: Autoencoding with Multiscale Coordinate Hashing
  122. Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise
  123. An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks
  124. On Robust Learning from Noisy Labels: A Permutation Layer Approach
  125. Simultaneous Best Subset Selection and Dimension Reduction via Primal-Dual Iterations
  126. UQ-ARMED: Uncertainty quantification of adversarially-regularized mixed effects deep learning for clustered non-iid data
  127. Approximating Martingale Process for Variance Reduction in Deep Reinforcement Learning with Large State Space
  128. Mirror descent of Hopfield model
  129. Effective Utilisation of Multiple Open-Source Datasets to Improve Generalisation Performance of Point Cloud Segmentation Models
  130. Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances
  131. Simultaneous Estimation of Hand Configurations and Finger Joint Angles using Forearm Ultrasound
  132. Fast Hyperparameter Tuning for Ising Machines
  133. Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos
  134. A Search and Detection Autonomous Drone System: from Design to Implementation
  135. Bayesian Experimental Design for Symbolic Discovery
  136. Distributed Energy Management and Demand Response in Smart Grids: A Multi-Agent Deep Reinforcement Learning Framework
  137. Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
  138. Disentangling the Mechanisms Behind Implicit Regularization in SGD
  139. ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information
  140. LUMix: Improving Mixup by Better Modelling Label Uncertainty
  141. Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
  142. Continuous Neural Algorithmic Planners
  143. Survey on Self-Supervised Multimodal Representation Learning and Foundation Models
  144. Guiding Neural Entity Alignment with Compatibility
  145. ExpNet: A unified network for Expert-Level Classification