mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 2 Jun 2023

266 papers

  1. Invisible Image Watermarks Are Provably Removable Using Generative AILLM safety and security → Watermarking generated content and models
  2. The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth EstimationDiffusion models → 3D, point cloud and scene generation
  3. On the Sample Complexity of Imitation Learning for Smoothed Model Predictive ControlOffline RL and imitation learning from data → Imitation learning methods
  4. Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized ExploitationDiffusion models → Robustness, privacy and adversarial aspects
  5. Conditional Generation from Unconditional Diffusion Models using Denoiser RepresentationsDiffusion models → Diffusion foundations and sampling
  6. Revisiting the Role of Language Priors in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. DiffECG: A Versatile Probabilistic Diffusion Model for ECG Signals SynthesisDiffusion models → Medical imaging and segmentation
  8. Probabilistic Adaptation of Text-to-Video ModelsWorld models → Video-generation world models and simulators
  9. Unifying (Machine) Vision via Counterfactual World ModelingWorld models → Latent predictive world models
  10. Video Colorization with Pre-trained Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  11. PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial RewardOffline RL and imitation learning from data → Imitation learning methods
  12. Denoising Diffusion Semantic Segmentation with Mask Prior ModelingDiffusion models → Medical imaging and segmentation
  13. Learning Multi-Step Reasoning by Solving Arithmetic TasksLLM reasoning → Mathematical reasoning
  14. Fine-Grained Human Feedback Gives Better Rewards for Language Model TrainingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  15. Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  16. DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response GenerationDiffusion models → Audio, speech and music
  17. Insights into Closed-form IPM-GAN Discriminator Guidance for Diffusion ModelingDiffusion models → Diffusion foundations and sampling
  18. Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel OptimizationLLM safety and security → Backdoor and data poisoning attacks
  19. PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  20. Audio-Visual Speech Enhancement with Score-Based Generative ModelsDiffusion models → Audio, speech and music
  21. Quantifying Sample Anonymity in Score-Based Generative Models with Adversarial FingerprintingDiffusion models → Robustness, privacy and adversarial aspects
  22. FedCIP: Federated Client Intellectual Property Protection with Traitor TrackingLLM safety and security → Federated unlearning and poisoning
  23. MathChat: Converse to Tackle Challenging Math Problems with LLM AgentsLLM agents and tool use → Educational agents and math problem solving
  24. Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  25. MetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  26. DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning DetectionLLM safety and security → Watermarking generated content and models
  27. An Overview on Generative AI at Scale with Edge-Cloud Computing
  28. VitalVideos-Europe: A dataset of face videos with PPG and blood pressure ground truths
  29. Image encryption for Offshore wind power based on 2D-LCLM and Zhou Yi Eight Trigrams
  30. A Hybrid Approach for Smart Alert Generation
  31. STUDY: Socially Aware Temporally Causal Decoder Recommender Systems
  32. Streaming Speech-to-Confusion Network Speech Recognition
  33. Sampling and Ranking for Digital Ink Generation on a tight computational budget
  34. ChatGPT is a Remarkable Tool -- For Experts
  35. A Survey on Explainability of Graph Neural Networks
  36. GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
  37. Efficient Spoken Language Recognition via Multilabel Classification
  38. EdGCon: Auto-assigner of Iconicity Ratings Grounded by Lexical Properties to Aid in Generation of Technical Gestures
  39. NLPositionality: Characterizing Design Biases of Datasets and Models
  40. Can Contextual Biasing Remain Effective with Whisper and GPT-2?
  41. AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
  42. Sampling binary sparse coding QUBO models using a spiking neuromorphic processor
  43. Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images
  44. LIC-GAN: Language Information Conditioned Graph Generative GAN Model
  45. Sub-Meter Tree Height Mapping of California using Aerial Images and LiDAR-Informed U-Net Model
  46. Simple Data Augmentation Techniques for Chinese Disease Normalization
  47. Structural Similarities Between Language Models and Neural Response Measurements
  48. Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work
  49. RITA: Group Attention is All You Need for Timeseries Analytics
  50. Improving the generalizability and robustness of large-scale traffic signal control
  51. Agnostic Multi-Group Active Learning
  52. Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
  53. In-the-wild Speech Emotion Conversion Using Disentangled Self-Supervised Representations and Neural Vocoder-based Resynthesis
  54. PDT: Pretrained Dual Transformers for Time-aware Bipartite Graphs
  55. A Simple yet Effective Self-Debiasing Framework for Transformer Models
  56. Synaptic motor adaptation: A three-factor learning rule for adaptive robotic control in spiking neural networks
  57. Overcoming the Stability Gap in Continual Learning
  58. Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
  59. Hierarchical Quadratic Random Forest Classifier
  60. DH-PTAM: A Deep Hybrid Stereo Events-Frames Parallel Tracking And Mapping System
  61. Mixed-type Distance Shrinkage and Selection for Clustering via Kernel Metric Learning
  62. Multifunctionality in a Connectome-Based Reservoir Computer
  63. SACSoN: Scalable Autonomous Control for Social Navigation
  64. Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
  65. Fast (1+varepsilon)-Approximation Algorithms for Binary Matrix Factorization
  66. Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domains
  67. No Bidding, No Regret: Pairwise-Feedback Mechanisms for Digital Goods and Data Auctions
  68. Spatially Resolved Gene Expression Prediction from H&E Histology Images via Bi-modal Contrastive Learning
  69. Knowledge of cultural moral norms in large language models
  70. 5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair
  71. Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
  72. Multi-Contrast Computed Tomography Atlas of Healthy Pancreas
  73. Open-world Text-specified Object Counting
  74. Lifting Architectural Constraints of Injective Flows
  75. Binary and Ternary Natural Language Generation
  76. Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework
  77. Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation
  78. ErfReLU: Adaptive Activation Function for Deep Neural Network
  79. Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems
  80. Comparative Analysis of Widely use Object-Oriented Languages
  81. Beta Thalassemia Carriers detection empowered federated Learning
  82. Heart Diseases Prediction Using Block-chain and Machine Learning
  83. Prediction of Citrus Diseases Using Machine Learning And Deep Learning: Classifier, Models SLR
  84. Fast Interactive Search with a Scale-Free Comparison Oracle
  85. Learning the effective order of a hypergraph dynamical system
  86. SAPI: Surroundings-Aware Vehicle Trajectory Prediction at Intersections
  87. DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference
  88. Adversarial Attack Based on Prediction-Correction
  89. Morphology Edge Attention Network and Optimal Geometric Matching Connection model for vascular segmentation
  90. Word Embeddings for Banking Industry
  91. OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection
  92. DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model
  93. Multilingual Conceptual Coverage in Text-to-Image Models
  94. DocFormerv2: Local Features for Document Understanding
  95. Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans
  96. Broadcasting in random recursive dags
  97. Streaming algorithms for evaluating noisy judges on unlabeled data -- binary classification
  98. Graph Sparsification for GCN Towards Optimal Crop Yield Predictions
  99. OMNI: Open-endedness via Models of human Notions of Interestingness
  100. A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
All 266
  1. Distilling Efficient Language-Specific Models for Cross-Lingual Transfer
  2. TIES-Merging: Resolving Interference When Merging Models
  3. Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?
  4. The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles
  5. Affinity Clustering Framework for Data Debiasing Using Pairwise Distribution Discrepancy
  6. Exploring Robustness of Image Recognition Models on Hardware Accelerators
  7. Evaluating Language Models for Mathematics through Interactions
  8. Uniform Convergence of Deep Neural Networks with Lipschitz Continuous Activation Functions and Variable Widths
  9. Context selectivity with dynamic availability enables lifelong continual learning
  10. Unique Brain Network Identification Number for Parkinson's Individuals Using Structural MRI
  11. MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates
  12. Harnessing large-language models to generate private synthetic text
  13. Balancing Exploration and Exploitation: Disentangled β-CVAE in De Novo Drug Design
  14. Neural Differential Recurrent Neural Network with Adaptive Time Steps
  15. XAI Renaissance: Redefining Interpretability in Medical Diagnostic Models
  16. Towards In-context Scene Understanding
  17. SourceP: Detecting Ponzi Schemes on Ethereum with Source Code
  18. An Adaptive Method for Weak Supervision with Drifting Data
  19. Backchannel Detection and Agreement Estimation from Video with Transformer Networks
  20. Poisoning Network Flow Classifiers
  21. Fair multilingual vandalism detection system for Wikipedia
  22. Federated Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation
  23. Auditing for Human Expertise
  24. Automatic Reconstruction of Semantic 3D Models from 2D Floor Plans
  25. Reduction of finite sampling noise in quantum neural networks
  26. Do we become wiser with time? On causal equivalence with tiered background knowledge
  27. Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations
  28. A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
  29. HomE: Homography-Equivariant Video Representation Learning
  30. Analyzing Credit Risk Model Problems through NLP-Based Clustering and Machine Learning: Insights from Validation Reports
  31. Centered Self-Attention Layers
  32. Decentralized Federated Learning: A Survey and Perspective
  33. Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning
  34. Two-View Geometry Scoring Without Correspondences
  35. A Novel Vision Transformer with Residual in Self-attention for Biomedical Image Classification
  36. Log Parsing: How Far Can ChatGPT Go?
  37. Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
  38. Learning from Partially Annotated Data: Example-aware Creation of Gap-filling Exercises for Language Learning
  39. EmoUS: Simulating User Emotions in Task-Oriented Dialogues
  40. Probabilistic Concept Bottleneck Models
  41. Spatio-Temporal Deep Learning-Assisted Reduced Security-Constrained Unit Commitment
  42. Segment Anything in High Quality
  43. An Attentive-based Generative Model for Medical Image Synthesis
  44. Comparing a composite model versus chained models to locate a nearest visual object
  45. Evaluating Machine Translation Quality with Conformal Predictive Distributions
  46. Publicly available datasets of breast histopathology H&E whole-slide images: A scoping review
  47. PassGPT: Password Modeling and (Guided) Generation with Large Language Models
  48. PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
  49. Does it pay to optimize AUC?
  50. Group channel pruning and spatial attention distilling for object detection
  51. Transformer-based Multi-Modal Learning for Multi Label Remote Sensing Image Classification
  52. Network Degeneracy as an Indicator of Training Performance: Comparing Finite and Infinite Width Angle Predictions
  53. One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms
  54. BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models
  55. Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations
  56. A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution
  57. Can LLMs like GPT-4 outperform traditional AI tools in dementia diagnosis? Maybe, but not today
  58. Data-Efficient French Language Modeling with CamemBERTa
  59. Accelerating science with human-aware artificial intelligence
  60. Local Message Passing on Frustrated Systems
  61. On Feature Diversity in Energy-based Models
  62. Robust low-rank training via approximate orthonormal constraints
  63. GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration
  64. Hierarchical Reinforcement Learning for Modeling User Novelty-Seeking Intent in Recommender Systems
  65. Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations
  66. Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning
  67. Guiding Text-to-Text Privatization by Syntax
  68. Understanding MLP-Mixer as a Wide and Sparse MLP
  69. GANs and alternative methods of synthetic noise generation for domain adaption of defect classification of Non-destructive ultrasonic testing
  70. Robust Bayesian Inference for Measurement Error Misspecification: The Berkson and Classical Cases
  71. Light Coreference Resolution for Russian with Hierarchical Discourse Features
  72. Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables
  73. ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
  74. Driving Context into Text-to-Text Privatization
  75. dugMatting: Decomposed-Uncertainty-Guided Matting
  76. Deep Q-Learning versus Proximal Policy Optimization: Performance Comparison in a Material Sorting Task
  77. SASMU: boost the performance of generalized recognition model using synthetic face dataset
  78. Unsupervised Extractive Summarization of Emotion Triggers
  79. Unsupervised Paraphrasing of Multiword Expressions
  80. Towards Robust FastSpeech 2 by Modelling Residual Multimodality
  81. A Modular Test Bed for Reinforcement Learning Incorporation into Industrial Applications
  82. Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
  83. Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection
  84. Multi-Objective Population Based Training
  85. Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics
  86. Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach
  87. On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directions
  88. A Closer Look at the Adversarial Robustness of Deep Equilibrium Models
  89. Improved DeepFake Detection Using Whisper Features
  90. Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model
  91. Break a Lag: Triple Exponential Moving Average for Enhanced Optimization
  92. Convergence analysis of equilibrium methods for inverse problems
  93. An Architecture for Deploying Reinforcement Learning in Industrial Environments
  94. The Flawed Foundations of Fair Machine Learning
  95. Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation
  96. Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
  97. Adaptive Attractors: A Defense Strategy against ML Adversarial Collusion Attacks
  98. Knowledge Graph Reasoning over Entities and Numerical Values
  99. Evaluating The Robustness of Self-Supervised Representations to Background/Foreground Removal
  100. Masked Autoencoder for Unsupervised Video Summarization
  101. Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT
  102. Chemical Property-Guided Neural Networks for Naphtha Composition Prediction
  103. ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?
  104. Task-Agnostic Structured Pruning of Speech Representation Models
  105. Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation
  106. Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training
  107. A systematic literature review on the code smells datasets and validation mechanisms
  108. DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities
  109. Robust and Generalisable Segmentation of Subtle Epilepsy-causing Lesions: a Graph Convolutional Approach
  110. Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
  111. DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents
  112. Energy-Efficient UAV-Assisted IoT Data Collection via TSP-Based Solution Space Reduction
  113. Adjustable Visual Appearance for Generalizable Novel View Synthesis
  114. Bilevel Fast Scene Adaptation for Low-Light Image Enhancement
  115. Covert Communication Based on the Poisoning Attack in Federated Learning
  116. Transformer-based Annotation Bias-aware Medical Image Segmentation
  117. Resource-Efficient Federated Hyperdimensional Computing
  118. Federated Domain Generalization: A Survey
  119. Navigating Fairness in Radiology AI: Concepts, Consequences,and Crucial Considerations
  120. Differentiable Grey-box Modelling of Phaser Effects using Frame-based Spectral Processing
  121. Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
  122. LyricSIM: A novel Dataset and Benchmark for Similarity Detection in Spanish Song LyricS
  123. Hyperparameters in Reinforcement Learning and How To Tune Them
  124. Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
  125. Text Style Transfer Back-Translation
  126. Independent Modular Networks
  127. Syntax-aware Hybrid prompt model for Few-shot multi-modal sentiment analysis
  128. EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
  129. Federated Learning Games for Reconfigurable Intelligent Surfaces via Causal Representations
  130. DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model
  131. Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation
  132. Egocentric Planning for Scalable Embodied Task Achievement
  133. LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning
  134. nnMobileNet: Rethinking CNN for Retinopathy Research
  135. KL-Divergence Guided Temperature Sampling
  136. Recent Advances in Graph-based Machine Learning for Applications in Smart Urban Transportation Systems
  137. Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification
  138. Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
  139. VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations
  140. On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
  141. Multi-Robot Path Planning Combining Heuristics and Multi-Agent Reinforcement Learning
  142. DeepScribe: Localization and Classification of Elamite Cuneiform Signs Via Deep Learning
  143. Self Contrastive Learning for Session-based Recommendation
  144. Calibrating Multimodal Learning
  145. Convex and Non-convex Optimization Under Generalized Smoothness
  146. Automatic Translation of Hate Speech to Non-hate Speech in Social Media Texts
  147. Collect-and-Distribute Transformer for 3D Point Cloud Analysis
  148. Mixture Proportion Estimation Beyond Irreducibility
  149. Transforming ECG Diagnosis:An In-depth Review of Transformer-based DeepLearning Models in Cardiovascular Disease Detection
  150. How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization?
  151. THiFLY Research at SemEval-2023 Task 7: A Multi-granularity System for CTR-based Textual Entailment and Evidence Retrieval
  152. Towards Sustainable Learning: Coresets for Data-efficient Deep Learning
  153. Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations
  154. Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators
  155. Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs
  156. Bayesian Regret Minimization in Offline Bandits
  157. Deep Reinforcement Learning Framework for Thoracic Diseases Classification via Prior Knowledge Guidance
  158. Exploring the Boundaries of Semi-Supervised Facial Expression Recognition using In-Distribution, Out-of-Distribution, and Unconstrained Data
  159. Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data
  160. Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?
  161. Predicting affinity ties in a surname network
  162. An Augmented Lagrangian Approach to Conically Constrained Non-monotone Variational Inequality Problems
  163. Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
  164. Linked Deep Gaussian Process Emulation for Model Networks
  165. A new method using deep transfer learning on ECG to predict the response to cardiac resynchronization therapy
  166. Counting Crowds in Bad Weather