mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 14 Oct 2022

250 papers

  1. Knowledge Distillation approach towards Melanoma DetectionKnowledge distillation → Distillation for medical imaging
  2. Eliciting Compatible Demonstrations for Multi-Human Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
  3. PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base PopulationLLM reasoning → Reasoning benchmarks and evaluation
  4. AVLEN: Audio-Visual-Language Embodied Navigation in 3D EnvironmentsWorld models → World models for navigation
  5. Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor AttacksLLM safety and security → Backdoor and data poisoning attacks
  6. Control, Confidentiality, and the Right to be ForgottenLLM safety and security → Machine unlearning
  7. EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  8. Robust Preference Learning for Storytelling via Contrastive Reinforcement LearningLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  9. Model-Based Imitation Learning for Urban DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  10. Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-trainingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  11. Learning Generalizable Models for Vehicle Routing Problems via Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  12. TransFusion: Transcribing Speech with Multinomial DiffusionDiffusion models → Audio, speech and music
  13. Enabling Classifiers to Make Judgements Explicitly Aligned with Human ValuesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  14. MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge RepresentationLLM reasoning → Reasoning benchmarks and evaluation
  15. Watermarking Pre-trained Language Models with BackdooringLLM safety and security → Watermarking generated content and models
  16. AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine TranslationMixture-of-experts → MoE large language models
  17. Can Language Representation Models Think in Bets?LLM reasoning → Reasoning benchmarks and evaluation
  18. Hierarchical Diffusion Models for Singing Voice Neural VocoderDiffusion models → Audio, speech and music
  19. Mutual Information Regularized Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  20. InFIP: An Explainable DNN Intellectual Property Protection Method based on Intrinsic FeaturesLLM safety and security → Watermarking generated content and models
  21. SQA3D: Situated Question Answering in 3D ScenesLLM reasoning → Spatial and embodied reasoning
  22. InterFair: Debiasing with Natural Language Feedback for Fair Interpretable PredictionsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  23. COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation
  24. Projecting Non-Fungible Token (NFT) Collections: A Contextual Generative Approach
  25. The Debate Over Understanding in AI's Large Language Models
  26. Hybrid Reinforced Medical Report Generation with M-Linear Attention and Repetition Penalty
  27. Multi-Head Cross-Attentional PPG and Motion Signal Fusion for Heart Rate Estimation
  28. RecipeMind: Guiding Ingredient Choices from Food Pairing to Recipe Completion using Cascaded Set Transformer
  29. AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks
  30. Artificial intelligence and renegotiation of commercial lease contracts affected by pandemic-related contingencies from Covid-19. The project A.I.A.Co
  31. 3rd Place Solution for Google Universal Image Embedding
  32. A Fault Detection Scheme Utilizing Convolutional Neural Network for PV Solar Panels with High Accuracy
  33. CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models
  34. MMTSA: Multimodal Temporal Segment Attention Network for Efficient Human Activity Recognition
  35. Segmentation-guided Domain Adaptation for Efficient Depth Completion
  36. Artificial Intelligence Nomenclature Identified From Delphi Study on Key Issues Related to Trust and Barriers to Adoption for Autonomous Systems
  37. Digital Image Forensics using Deep Learning
  38. ST-former for short-term passenger flow prediction during COVID-19 in urban rail transit system
  39. Approximation analysis of CNNs from a feature extraction view
  40. WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments
  41. Periodic Artifact Reduction in Fourier transforms of Full Field Atomic Resolution Images
  42. Self-Repetition in Abstractive Neural Summarizers
  43. Pseudo AI Bias
  44. A Kernel Approach for PDE Discovery and Operator Learning
  45. Partial Identification of Treatment Effects with Implicit Generative Models
  46. VHetNets for AI and AI for VHetNets: An Anomaly Detection Case Study for Ubiquitous IoT
  47. Model-Free Characterizations of the Hamilton-Jacobi-Bellman Equation and Convex Q-Learning in Continuous Time
  48. TweetNERD -- End to End Entity Linking Benchmark for Tweets
  49. Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation
  50. Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again
  51. Instance Segmentation with Cross-Modal Consistency
  52. A Multistep Frank-Wolfe Method
  53. A Primal-Dual Algorithm for Hybrid Federated Learning
  54. High-resolution synthetic residential energy use profiles for the United States
  55. Budget-Aware Pruning for Multi-Domain Learning
  56. TestAug: A Framework for Augmenting Capability-based NLP Tests
  57. Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty
  58. Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
  59. Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
  60. Adaptive patch foraging in deep reinforcement learning agents
  61. Reference Based Color Transfer for Medical Volume Rendering
  62. Deep Learning based Super-Resolution for Medical Volume Visualization with Direct Volume Rendering
  63. Zonotope Domains for Lagrangian Neural Network Verification
  64. Whole-body tumor segmentation of 18F -FDG PET/CT using a cascaded and ensembled convolutional neural networks
  65. Optimizing Vision Transformers for Medical Image Segmentation
  66. Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion
  67. LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds
  68. Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
  69. Pishgu: Universal Path Prediction Network Architecture for Real-time Cyber-physical Edge Systems
  70. Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment
  71. Multi-trainer Interactive Reinforcement Learning System
  72. Injecting Domain Knowledge from Empirical Interatomic Potentials to Neural Networks for Predicting Material Properties
  73. Differentiable Hybrid Traffic Simulation
  74. Meta Transferring for Deblurring
  75. Neural Attentive Circuits
  76. Prediction of drug effectiveness in rheumatoid arthritis patients based on machine learning algorithms
  77. On the Relationship Between Variational Inference and Auto-Associative Memory
  78. Autoencoder based Anomaly Detection and Explained Fault Localization in Industrial Cooling Systems
  79. Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
  80. Lambda-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
  81. Degeneracy is OK: Logarithmic Regret for Network Revenue Management with Indiscrete Distributions
  82. MiQA: A Benchmark for Inference on Metaphorical Questions
  83. A Variational Perspective on Generative Flow Networks
  84. Novel 3D Scene Understanding Applications From Recurrence in a Single Image
  85. Bayesian Learning via Q-Exponential Process
  86. αQBoost: An Iteratively Weighted Adiabatic Trained Classifier
  87. Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification
  88. Representation Theory for Geometric Quantum Machine Learning
  89. Improving generalizability of distilled self-supervised speech processing models under distorted settings
  90. Wide Range MRI Artifact Removal with Transformers
  91. Data-Limited Tissue Segmentation using Inpainting-Based Self-Supervised Learning
  92. Neural Routing in Meta Learning
  93. Sequential Learning Of Neural Networks for Prequential MDL
  94. MOVE: Unsupervised Movable Object Segmentation and Detection
  95. A Hybrid Partitioning Strategy for Backward Reachability of Neural Feedback Loops
  96. Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition
  97. Efficiently Controlling Multiple Risks with Pareto Testing
  98. Post-Training Quantization for Energy Efficient Realization of Deep Neural Networks
  99. HashFormers: Towards Vocabulary-independent Pre-trained Transformers
  100. Text Detection Forgot About Document OCR
All 250
  1. Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees
  2. Hierarchical Policy Blending as Inference for Reactive Robot Control
  3. E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories
  4. PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning
  5. One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations
  6. Communication-Efficient Topologies for Decentralized Learning with O(1) Consensus Rate
  7. Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations
  8. Hierarchical Approach for Joint Semantic, Plant Instance, and Leaf Instance Segmentation in the Agricultural Domain
  9. A Second Wave of UD Hebrew Treebanking and Cross-Domain Parsing
  10. One Graph to Rule them All: Using NLP and Graph Neural Networks to analyse Tolkien's Legendarium
  11. Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization
  12. Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images
  13. Commutativity and Disentanglement from the Manifold Perspective
  14. Bringing NURC/SP to Digital Life: the Role of Open-source Automatic Speech Recognition Models
  15. Learning to Autonomously Reach Objects with NICO and Grow-When-Required Networks
  16. Convolutional Neural Networks: Basic Concepts and Applications in Manufacturing
  17. Flame-state monitoring based on very low number of visible or infrared images via few-shot learning
  18. Asymmetric Student-Teacher Networks for Industrial Anomaly Detection
  19. Parameter-Free Average Attention Improves Convolutional Neural Network Performance (Almost) Free of Charge
  20. Shadfa 0.1: The Iranian Movie Knowledge Graph and Graph-Embedding-Based Recommender System
  21. ISTA-Inspired Network for Image Super-Resolution
  22. Surface abnormality detection in medical and inspection systems using energy variations in co-occurrence matrixes
  23. SAILOR: Scaling Anchors via Insights into Latent Object Representation
  24. Comparison of different automatic solutions for resection cavity segmentation in postoperative MRI volumes including longitudinal acquisitions
  25. Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
  26. Federated Best Arm Identification with Heterogeneous Clients
  27. LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue
  28. Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
  29. Activity-aware Human Mobility Prediction with Hierarchical Graph Attention Recurrent Network
  30. Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization
  31. Extracting Cultural Commonsense Knowledge at Scale
  32. Controllable Style Transfer via Test-time Training of Implicit Neural Representation
  33. Improved automated lesion segmentation in whole-body FDG/PET-CT via Test-Time Augmentation
  34. Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning
  35. Simpson's Paradox in Recommender Fairness: Reconciling differences between per-user and aggregated evaluations
  36. Blind Super-Resolution for Remote Sensing Images via Conditional Stochastic Normalizing Flows
  37. Bandwidth-efficient distributed neural network architectures with application to body sensor networks
  38. Confidence estimation of classification based on the distribution of the neural network output layer
  39. Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning
  40. Privacy-Preserving and Lossless Distributed Estimation of High-Dimensional Generalized Additive Mixed Models
  41. (1,1)-Cluster Editing is Polynomial-time Solvable
  42. A Lightweight Moving Target Defense Framework for Multi-purpose Malware Affecting IoT Devices
  43. Motion-related Artefact Classification Using Patch-based Ensemble and Transfer Learning in Cardiac MRI
  44. Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning
  45. CrowdGuard: Federated Backdoor Detection in Federated Learning
  46. An Empirical Evaluation of Multivariate Time Series Classification with Input Transformation across Different Dimensions
  47. Generative Adversarial Learning for Trusted and Secure Clustering in Industrial Wireless Sensor Networks
  48. Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence
  49. Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources
  50. Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey
  51. Multi-Task Learning based Video Anomaly Detection with Attention
  52. Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization
  53. Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
  54. Learning image representations for anomaly detection: application to discovery of histological alterations in drug development
  55. Multi-View Photometric Stereo Revisited
  56. Pretrained Transformers Do not Always Improve Robustness
  57. CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling
  58. Automated dysgraphia detection by deep learning with SensoGrip
  59. Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
  60. Towards Transformer-based Homogenization of Satellite Imagery for Landsat-8 and Sentinel-2
  61. Decentralized Policy Gradient for Nash Equilibria Learning of General-sum Stochastic Games
  62. DART: Articulated Hand Model with Diverse Accessories and Rich Textures
  63. Machine Learning in Transaction Monitoring: The Prospect of xAI
  64. Vision Transformer Visualization: What Neurons Tell and How Neurons Behave?
  65. Training speech emotion classifier without categorical annotations
  66. Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning
  67. Pareto-aware Neural Architecture Generation for Diverse Computational Budgets
  68. Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task
  69. The Invariant Ground Truth of Affect
  70. BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
  71. Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths
  72. Quantifying Quality of Class-Conditional Generative Models in Time-Series Domain
  73. FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning
  74. Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
  75. Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion
  76. Revisiting Heterophily For Graph Neural Networks
  77. Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution
  78. MCTNet: A Multi-Scale CNN-Transformer Network for Change Detection in Optical Remote Sensing Images
  79. Lightweight Stepless Super-Resolution of Remote Sensing Images via Saliency-Aware Dynamic Routing Strategy
  80. The State of Profanity Obfuscation in Natural Language Processing
  81. See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
  82. Distributed Distributionally Robust Optimization with Non-Convex Objectives
  83. ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining
  84. Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations
  85. Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling
  86. MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation
  87. Is synthetic data from generative models ready for image recognition?
  88. Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm
  89. Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding
  90. Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
  91. A Survey of Parameters Associated with the Quality of Benchmarks in NLP
  92. Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning
  93. Q-TOD: A Query-driven Task-oriented Dialogue System
  94. TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
  95. Empirical Study Incorporating Linguistic Knowledge on Filled Pauses for Personalized Spontaneous Speech Synthesis
  96. DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation
  97. Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
  98. Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection
  99. Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
  100. Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario
  101. Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation
  102. Uncertainty Quantification and Sensitivity analysis for Digital Twin Enabling Technology: Application for BISON Fuel Performance Code
  103. When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
  104. Superpixel perception graph neural network for intelligent defect detection of aero-engine blade
  105. The User-Aware Arabic Gender Rewriter
  106. A Reinforcement Learning Approach to Estimating Long-term Treatment Effects
  107. Provable Subspace Identification Under Post-Nonlinear Mixtures
  108. Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge
  109. Spatiotemporal Classification with limited labels using Constrained Clustering for large datasets
  110. Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media
  111. Continuous-in-time Limit for Bayesian Bandits
  112. Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique
  113. Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
  114. Learning Active Camera for Multi-Object Navigation
  115. STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition
  116. ToupleGDD: A Fine-Designed Solution of Influence Maximization by Deep Reinforcement Learning
  117. Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks
  118. A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
  119. Psychology-guided Controllable Story Generation
  120. Exploring Vanilla U-Net for Lesion Segmentation from Whole-body FDG-PET/CT Scans
  121. The Surprisingly Straightforward Scene Text Removal Method With Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis
  122. MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks
  123. A Scalable Finite Difference Method for Deep Reinforcement Learning
  124. Holistic Sentence Embeddings for Better Out-of-Distribution Detection
  125. Latent Temporal Flows for Multivariate Analysis of Wearables Data
  126. Robust Candidate Generation for Entity Linking on Short Social Media Texts
  127. "John is 50 years old, can his son be 65?" Evaluating NLP Models' Understanding of Feasibility
  128. StyLEx: Explaining Style Using Human Lexical Annotations
  129. Transparency Helps Reveal When Language Models Learn Meaning
  130. Query Rewriting for Effective Misinformation Discovery
  131. Synthetic-to-real Composite Semantic Segmentation in Additive Manufacturing
  132. Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation
  133. Estimation of High-Dimensional Markov-Switching VAR Models with an Approximate EM Algorithm
  134. Controlling Bias Exposure for Fair Interpretable Predictions
  135. Communication-Efficient Adam-Type Algorithms for Distributed Data Mining
  136. Using Graph Algorithms to Pretrain Graph Completion Transformers
  137. Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction
  138. ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation
  139. G2A2: An Automated Graph Generator with Attributes and Anomalies
  140. Evaluating Out-of-Distribution Performance on Document Image Classifiers
  141. Multilingual Word Sense Disambiguation with Unified Sense Representation
  142. Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds
  143. Characterizing the Influence of Graph Elements
  144. Risk-Awareness in Learning Neural Controllers for Temporal Logic Objectives
  145. Smart Headset, Computer Vision and Machine Learning for Efficient Prawn Farm Management
  146. NOCaL: Calibration-Free Semi-Supervised Learning of Odometry and Camera Intrinsics
  147. Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations
  148. PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation
  149. CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation
  150. Skill-Based Reinforcement Learning with Intrinsic Reward Matching