mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 20 Jul 2023

240 papers

  1. From Adaptive Query Release to Machine UnlearningLLM safety and security → Machine unlearning
  2. UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  3. Dehazing Ultrasound using Diffusion ModelsDiffusion models → Medical imaging and segmentation
  4. Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  5. Diffusion Models for Probabilistic Deconvolution of Galaxy ImagesDiffusion models → Inverse problems and image restoration
  6. Diffusion Sampling with Momentum for Mitigating Divergence ArtifactsDiffusion models → Diffusion foundations and sampling
  7. Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  8. Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns ClusteringKnowledge distillation → General knowledge distillation methods
  9. PASTA: Pretrained Action-State Transformer AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
  10. FLASK: Fine-grained Language Model Evaluation based on Alignment Skill SetsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  11. FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human FeedbackLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  12. Divide & Bind Your Attention for Improved Generative Semantic NursingDiffusion models → Image generation, text-to-image and editing
  13. BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained DiffusionDiffusion models → Image generation, text-to-image and editing
  14. On Combining Expert Demonstrations in Imitation Learning via Optimal TransportOffline RL and imitation learning from data → Imitation learning methods
  15. Learned Thresholds Token Merging and Pruning for Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
  16. AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
  17. Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited DataKnowledge distillation → Distillation for medical imaging
  18. Quantized Feature Distillation for Network QuantizationKnowledge distillation → Knowledge distillation for LLMs
  19. SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language ModelsLLM reasoning → Mathematical reasoning
  20. Multi-Method Self-Training: Improving Code Generation With Text, And Vice VersaSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  21. Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model PromptingLLM reasoning → Prompting and chain-of-thought reasoning
  22. IvyGPT: InteractiVe Chinese pathwaY language model in medical domainLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  23. Data Analytics with Differential Privacy
  24. Unveiling Emotions from EEG: A GRU-Based Approach
  25. What Twitter Data Tell Us about the Future?
  26. A LLM Assisted Exploitation of AI-Guardian
  27. General Image-to-Image Translation with One-Shot Image Guidance
  28. Leveraging arbitrary mobile sensor trajectories with shallow recurrent decoder networks for full-state reconstruction
  29. Quantum Convolutional Neural Networks with Interaction Layers for Classification of Classical Data
  30. Applying QNLP to sentiment analysis in finance
  31. LLM Cognitive Judgements Differ From Human
  32. Adversarial Conversational Shaping for Intelligent Agents
  33. What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
  34. A novel integrated method of detection-grasping for specific object based on the box coordinate matching
  35. Convergence of Adam for Non-convex Objectives: Relaxed Hyperparameters and Non-ergodic Case
  36. The Extractive-Abstractive Axis: Measuring Content "Borrowing" in Generative Language Models
  37. Transsion TSUP's speech recognition system for ASRU 2023 MADASR Challenge
  38. Prediction of Handball Matches with Statistically Enhanced Learning via Estimated Team Strengths
  39. SimCol3D -- 3D Reconstruction during Colonoscopy Challenge
  40. Investigating Low Data, Confidence Aware Image Prediction on Smooth Repetitive Videos using Gaussian Processes
  41. An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing
  42. Joint one-sided synthetic unpaired image translation and segmentation for colorectal cancer prevention
  43. On the Natural Gradient of the Evidence Lower Bound
  44. On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments
  45. Edgewise outliers of network indexed signals
  46. QDC: Quantum Diffusion Convolution Kernels on Graphs
  47. Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
  48. FairMobi-Net: A Fairness-aware Deep Learning Model for Urban Mobility Flow Generation
  49. The Effect of Epidemiological Cohort Creation on the Machine Learning Prediction of Homelessness and Police Interaction Outcomes Using Administrative Health Care Data
  50. Clinical Trial Active Learning
  51. Towards Ontologically Grounded and Language-Agnostic Knowledge Graphs
  52. Heuristic Hyperparameter Choice for Image Anomaly Detection
  53. UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition
  54. Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment
  55. Towards General Game Representations: Decomposing Games Pixels into Content and Style
  56. Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network
  57. Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications
  58. Asymptotically Unbiased Synthetic Control Methods by Moment Matching
  59. A Markov Chain Model for Identifying Changes in Daily Activity Patterns of People Living with Dementia
  60. The Nature of Intelligence
  61. Comparison between transformers and convolutional models for fine-grained classification of insects
  62. Flatness-Aware Minimization for Domain Generalization
  63. Data-driven criteria for quantum correlations
  64. L-Eval: Instituting Standardized Evaluation for Long Context Language Models
  65. PAPR: Proximity Attention Point Rendering
  66. Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challenge
  67. GLSFormer: Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos
  68. Brain2Music: Reconstructing Music from Human Brain Activity
  69. AlignDet: Aligning Pre-training and Fine-tuning in Object Detection
  70. Learning Dense UV Completion for Human Mesh Recovery
  71. OBJECT 3DIT: Language-guided 3D-aware Image Editing
  72. Effectiveness and predictability of in-network storage cache for scientific workflows
  73. CNOS: A Strong Baseline for CAD-based Novel Object Segmentation
  74. Anticipating Driving Behavior through Deep Learning-Based Policy Prediction
  75. HRFNet: High-Resolution Forgery Network for Localizing Satellite Image Manipulation
  76. A Definition of Continual Reinforcement Learning
  77. On the Convergence of Bounded Agents
  78. Cascade-DETR: Delving into High-Quality Universal Object Detection
  79. Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
  80. Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
  81. Amortized Variational Inference: When and Why?
  82. Multi-objective point cloud autoencoders for explainable myocardial infarction prediction
  83. Flow Map Learning for Unknown Dynamical Systems: Overview, Implementation, and Benchmarks
  84. Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing
  85. Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization
  86. Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding
  87. NeoSySPArtaN: A Neuro-Symbolic Spin Prediction Architecture for higher-order multipole waveforms from eccentric Binary Black Hole mergers using Numerical Relativity
  88. Private Federated Learning with Autotuned Compression
  89. DREAM: Domain-free Reverse Engineering Attributes of Black-box Model
  90. Progressive distillation diffusion for raw music generation
  91. Dense Sample Deep Learning
  92. On minimizing the training set fill distance in machine learning regression
  93. Characterising Decision Theories with Mechanised Causal Graphs
  94. Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
  95. MASR: Multi-label Aware Speech Representation
  96. PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks
  97. Globally Normalising the Transducer for Streaming Speech Recognition
  98. Deep Multi-Threshold Spiking-UNet for Image Processing
  99. Spinal nerve segmentation method and dataset construction in endoscopic surgical scenarios
  100. Soft-tissue Driven Craniomaxillofacial Surgical Planning
All 240
  1. PE-YOLO: Pyramid Enhancement Network for Dark Object Detection
  2. Improving Online Lane Graph Extraction by Object-Lane Clustering
  3. Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery
  4. Inorganic synthesis-structure maps in zeolites with machine learning and crystallographic distances
  5. OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios
  6. Identical and Fraternal Twins: Fine-Grained Semantic Contrastive Learning of Sentence Representations
  7. MediaGPT : A Large Language Model For Chinese Media
  8. Modeling 3D cardiac contraction and relaxation with point cloud deformation networks
  9. Confidence Intervals for Performance Estimates in Brain MRI Segmentation
  10. Intrinsic Image Decomposition Using Point Cloud Representation
  11. Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series
  12. Language-based Action Concept Spaces Improve Video Self-Supervised Learning
  13. Revisiting Fine-Tuning Strategies for Self-supervised Medical Imaging Analysis
  14. WeakPolyp: You Only Look Bounding Box for Polyp Segmentation
  15. The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
  16. Variational Autoencoding of Dental Point Clouds
  17. Human Motion Generation: A Survey
  18. Learning and Generalizing Polynomials in Simulation Metamodeling
  19. Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networks
  20. Player-optimal Stable Regret for Bandit Learning in Matching Markets
  21. Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification
  22. Conservative Estimation of Perception Relevance of Dynamic Objects for Safe Trajectories in Automotive Scenarios
  23. Nonlinear Meta-Learning Can Guarantee Faster Rates
  24. Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features
  25. Addressing caveats of neural persistence with deep graph persistence
  26. BlendFace: Re-designing Identity Encoders for Face-Swapping
  27. Exploring Effective Priors and Efficient Models for Weakly-Supervised Change Detection
  28. Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning
  29. Self-paced Weight Consolidation for Continual Learning
  30. Global Precipitation Nowcasting of Integrated Multi-satellitE Retrievals for GPM: A U-Net Convolutional LSTM Architecture
  31. Label Calibration for Semantic Segmentation Under Domain Shift
  32. Modifications of the Miller definition of contrastive (counterfactual) explanations
  33. Yelp Reviews and Food Types: A Comparative Analysis of Ratings, Sentiments, and Topics
  34. Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists
  35. Gradient-Semantic Compensation for Incremental Semantic Segmentation
  36. Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages
  37. Perceptual Quality Assessment of Omnidirectional Audio-visual Signals
  38. "It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Models
  39. Communication-Efficient Split Learning via Adaptive Feature-Wise Compression
  40. Spatial-Temporal Data Mining for Ocean Science: Data, Methodologies, and Opportunities
  41. Meta-Transformer: A Unified Framework for Multimodal Learning
  42. Layer-wise Representation Fusion for Compositional Generalization
  43. HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces
  44. Optimizing PatchCore for Few/many-shot Anomaly Detection
  45. Behavioral Analysis of Vision-and-Language Navigation Agents
  46. Adversarial attacks for mixtures of classifiers
  47. Feed-Forward Source-Free Domain Adaptation via Class Prototypes
  48. SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radar
  49. See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
  50. Efficient Beam Tree Recursion
  51. Extreme Multi-Label Skill Extraction Training using Large Language Models
  52. Urban Radiance Field Representation with Deformable Neural Mesh Primitives
  53. Assessing the Use of AutoML for Data-Driven Software Engineering
  54. Music Genre Classification with ResNet and Bi-GRU Using Visual Spectrograms
  55. Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
  56. Actor-agnostic Multi-label Action Recognition with Multi-modal Query
  57. Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition
  58. LBL: Logarithmic Barrier Loss Function for One-class Classification
  59. Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work: Beyond Mechanised Plagiarism and Stochastic Parrots
  60. Mitigating Voter Attribute Bias for Fair Opinion Aggregation
  61. EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation
  62. Fairness-Aware Client Selection for Federated Learning
  63. Long-Tail Theory under Gaussian Mixtures
  64. LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
  65. Differences Between Hard and Noisy-labeled Samples: An Empirical Study
  66. Introducing Risk Shadowing For Decisive and Comfortable Behavior Planning
  67. Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV
  68. Reparameterized Policy Learning for Multimodal Trajectory Optimization
  69. TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars
  70. Decentralized Smart Charging of Large-Scale EVs using Adaptive Multi-Agent Multi-Armed Bandits
  71. Graphs in State-Space Models for Granger Causality in Climate Science
  72. Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers
  73. SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning
  74. SLPD: Slide-level Prototypical Distillation for WSIs
  75. Self2Self+: Single-Image Denoising with Self-Supervised Learning and Image Quality Assessment Loss
  76. Towards an architectural framework for intelligent virtual agents using probabilistic programming
  77. Bounded Combinatorial Reconfiguration with Answer Set Programming
  78. Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection
  79. Fractional Denoising for 3D Molecular Pre-training
  80. A Personalized Recommender System Based-on Knowledge Graph Embeddings
  81. Deep learning for classification of noisy QR codes
  82. Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors
  83. A Dataset and Strong Baselines for Classification of Czech News Texts
  84. Lighting up NeRF via Unsupervised Decomposition and Enhancement
  85. A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
  86. Conditional expectation network for SHAP
  87. Refining the Optimization Target for Automatic Univariate Time Series Anomaly Detection in Monitoring Services
  88. Exploring the Landscape of Natural Language Processing Research
  89. Data-Driven Latency Probability Prediction for Wireless Networks: Focusing on Tail Probabilities
  90. Fisher-Rao distance and pullback SPD cone distances between multivariate normal distributions
  91. RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection
  92. Learning and Evaluating Human Preferences for Conversational Head Generation
  93. Generative Language Models on Nucleotide Sequences of Human Genes
  94. Parallelization of a new embedded application for automatic meteor detection
  95. Pluvio: Assembly Clone Search for Out-of-domain Architectures and Libraries through Transfer Learning and Conditional Variational Information Bottleneck
  96. Learning Discriminative Visual-Text Representation for Polyp Re-Identification
  97. Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification
  98. Quaternion tensor left ring decomposition and application for color image inpainting
  99. Unmasking Falsehoods in Reviews: An Exploration of NLP Techniques
  100. Heterogeneous Federated Learning: State-of-the-art and Research Challenges
  101. Hybrid Feature Embedding For Automatic Building Outline Extraction
  102. Physics-Driven Turbulence Image Restoration with Stochastic Refinement
  103. SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrieval
  104. Challenges and Solutions in AI for All
  105. Ensemble Learning based Anomaly Detection for IoT Cybersecurity via Bayesian Hyperparameters Sensitivity Analysis
  106. Exploiting Structure for Optimal Multi-Agent Bayesian Decentralized Estimation
  107. Asynchronous Blob Tracker for Event Cameras
  108. Boundary State Generation for Testing and Improvement of Autonomous Driving Systems
  109. Forecasting Battery Electric Vehicle Charging Behavior: A Deep Learning Approach Equipped with Micro-Clustering and SMOTE Techniques
  110. A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos
  111. A Holistic Assessment of the Reliability of Machine Learning Systems
  112. Reference-based Painterly Inpainting via Diffusion: Crossing the Wild Reference Domain Gap
  113. Intelligent model for offshore China sea fog forecasting
  114. SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning
  115. Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding & Contextual Label Affinity
  116. Boosting Federated Learning Convergence with Prototype Regularization
  117. Adaptive Control of Resource Flow to Optimize Construction Work and Cash Flow via Online Deep Reinforcement Learning
  118. Deceptive Alignment Monitoring
  119. No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection
  120. FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation
  121. Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
  122. Post-variational quantum neural networks
  123. Air Traffic Controller Workload Level Prediction using Conformalized Dynamical Graph Learning
  124. Instruction-following Evaluation through Verbalizer Manipulation
  125. EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
  126. PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts
  127. SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer
  128. Dynamic Large Language Models on Blockchains
  129. TREA: Tree-Structure Reasoning Schema for Conversational Recommendation
  130. Differentially Flat Learning-based Model Predictive Control Using a Stability, State, and Input Constraining Safety Filter
  131. Multiply Robust Estimator Circumvents Hyperparameter Tuning of Neural Network Models in Causal Inference
  132. Fast Unsupervised Deep Outlier Model Selection with Hypernetworks
  133. Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions
  134. Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models
  135. Interactive Segmentation for Diverse Gesture Types Without Context
  136. Building Socio-culturally Inclusive Stereotype Resources with Community Engagement
  137. General Debiasing for Multimodal Sentiment Analysis
  138. FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation
  139. Is Grad-CAM Explainable in Medical Images?
  140. Identifying Interpretable Subspaces in Image Representations