mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 12 Jun 2023

224 papers

  1. Deep Ultrasound Denoising Using Diffusion Probabilistic ModelsDiffusion models → Medical imaging and segmentation
  2. Waffling around for Performance: Visual Classification with Random Words and Broad ConceptsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  3. Controlling Text-to-Image Diffusion by Orthogonal FinetuningDiffusion models → Image generation, text-to-image and editing
  4. Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  5. Gaussian Membership Inference PrivacyLLM safety and security → Membership inference attacks
  6. A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine TranslationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage TrainingRetrieval-augmented generation → Generation and context integration
  8. Diffusion Models for Black-Box OptimizationDiffusion models → Diffusion foundations and sampling
  9. Global and Local Semantic Completion Learning for Vision-Language Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Latent Dynamical Implicit Diffusion ProcessesDiffusion models → Diffusion foundations and sampling
  11. Revisiting Token Pruning for Object Detection and Instance SegmentationEfficient LLM inference and serving → Token pruning and merging for ViTs
  12. Fast Diffusion ModelDiffusion models → Diffusion foundations and sampling
  13. Potential Field-based Path Planning with Interactive Speed Optimization for Autonomous VehiclesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  14. Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language ModelsLLM reasoning → Test-time compute and efficient thinking
  15. VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  16. ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-EnsemblesOffline RL and imitation learning from data → Offline RL algorithms
  17. HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion ModelsDiffusion models → Audio, speech and music
  18. Mapping Global Value Chains at the Product Level
  19. weighted CapsuleNet networks for Persian multi-domain sentiment analysis
  20. Interpolating Item and User Fairness in Multi-Sided Recommendations
  21. Neighborhood-based Hard Negative Mining for Sequential Recommendation
  22. Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs
  23. Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction
  24. A Practical Entity Linking System for Tables in Scientific Literature
  25. MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition
  26. Contrastive Attention Networks for Attribution of Early Modern Print
  27. Machine Learning Approach on Multiclass Classification of Internet Firewall Log Files
  28. Point spread function modelling for astronomical telescopes: a review focused on weak gravitational lensing studies
  29. Semantic-Based Neural Network Repair
  30. MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
  31. Trustworthy Artificial Intelligence Framework for Proactive Detection and Risk Explanation of Cyber Attacks in Smart Grid
  32. A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
  33. Unlocking Sales Growth: Account Prioritization Engine with Explainable AI
  34. On the Robustness of Removal-Based Feature Attributions
  35. Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressure
  36. Accurate Measures of Vaccination and Concerns of Vaccine Holdouts from Web Search Logs
  37. Getting the Most from Eye-Tracking: User-Interaction Based Reading Region Estimation Dataset and Models
  38. Instant Multi-View Head Capture through Learnable Registration
  39. FIRE: An Optimization Approach for Fast Interpretable Rule Extraction
  40. Explaining CLIP through Co-Creative Drawings and Interaction
  41. Towards Fair and Explainable AI using a Human-Centered AI Approach
  42. Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati
  43. DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skills
  44. Synaptic Scaling and Optimal Bias Adjustments for Power Reduction in Neuromorphic Systems
  45. Gender-Inclusive Grammatical Error Correction through Augmentation
  46. Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili
  47. Robust Reinforcement Learning through Efficient Adversarial Herding
  48. Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation
  49. Enhancing Topic Extraction in Recommender Systems with Entropy Regularization
  50. 4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements
  51. Adversarial Attacks on the Interpretation of Neuron Activation Maximization
  52. Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering
  53. Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling
  54. Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions
  55. "Private Prediction Strikes Back!'' Private Kernelized Nearest Neighbors with Individual Renyi Filter
  56. Lost in Translation: Large Language Models in Non-English Content Analysis
  57. EriBERTa: A Bilingual Pre-Trained Language Model for Clinical Natural Language Processing
  58. Composing Efficient, Robust Tests for Policy Selection
  59. Intelligent Multi-channel Meta-imagers for Accelerating Machine Vision
  60. H-SLAM: Hybrid Direct-Indirect Visual SLAM
  61. HDDL 2.1: Towards Defining a Formalism and a Semantics for Temporal HTN Planning
  62. Multi-Platform Budget Management in Ad Markets with Non-IC Auctions
  63. G-invariant diffusion maps
  64. Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training
  65. Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data
  66. Splitting and Parallelizing of Quantum Convolutional Neural Networks for Learning Translationally Symmetric Data
  67. Employing Crowdsourcing for Enriching a Music Knowledge Base in Higher Education
  68. A New Probabilistic Distance Metric With Application In Gaussian Mixture Reduction
  69. Self-Supervised Hyperspectral Inpainting with the Optimisation inspired Deep Neural Network Prior
  70. Online Prototype Alignment for Few-shot Policy Transfer
  71. Active Globally Explainable Learning for Medical Images via Class Association Embedding and Cyclic Adversarial Generation
  72. Making forecasting self-learning and adaptive -- Pilot forecasting rack
  73. No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection
  74. Scalable 3D Captioning with Pretrained Models
  75. Mathematical conjecture generation using machine intelligence
  76. CryoChains: Heterogeneous Reconstruction of Molecular Assembly of Semi-flexible Chains from Cryo-EM Images
  77. Zero-shot Composed Text-Image Retrieval
  78. Operator Learning with Neural Fields: Tackling PDEs on General Geometries
  79. detrex: Benchmarking Detection Transformers
  80. Unprocessing Seven Years of Algorithmic Fairness
  81. MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images
  82. Conditional Matrix Flows for Gaussian Graphical Models
  83. On the Expected Size of Conformal Prediction Sets
  84. On the Validity of Conformal Prediction for Network Data Under Non-Uniform Sampling
  85. Reliable machine learning potentials based on artificial neural network for graphene
  86. RB-Dust -- A Reference-based Dataset for Vision-based Dust Removal
  87. Deep Gaussian Mixture Ensembles
  88. Generative Plug and Play: Posterior Sampling for Inverse Problems
  89. Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction
  90. Strokes2Surface: Recovering Curve Networks From 4D Architectural Design Sketches
  91. A Protocol for Continual Explanation of SHAP
  92. Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
  93. Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision
  94. Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow
  95. Valley: Video Assistant with Large Language model Enhanced abilitY
  96. RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation
  97. LTCR: Long-Text Chinese Rumor Detection Dataset
  98. Fill-Up: Balancing Long-Tailed Data with Generative Models
  99. AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation
  100. Retrieval-Enhanced Contrastive Vision-Text Models
All 224
  1. Large language models and (non-)linguistic recursion
  2. Inference-time Stochastic Ranking with Risk Control
  3. Video-to-Music Recommendation using Temporal Alignment of Segments
  4. CD-CTFM: A Lightweight CNN-Transformer Network for Remote Sensing Cloud Detection Fusing Multiscale Features
  5. The Effect of Masking Strategies on Knowledge Retention by Language Models
  6. Benchmarking Neural Network Training Algorithms
  7. Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions
  8. Slicing Unbalanced Optimal Transport
  9. Augmenting Language Models with Long-Term Memory
  10. Shapley Value on Probabilistic Classifiers
  11. Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning
  12. Explainable AI and Machine Learning Towards Human Gait Deterioration Analysis
  13. A Batch-to-Online Transformation under Random-Order Model
  14. On the Computation-Communication Trade-Off with A Flexible Gradient Tracking Approach
  15. Riemannian Laplace approximations for Bayesian neural networks
  16. InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions
  17. Measuring Sentiment Bias in Machine Translation
  18. Evolving Testing Scenario Generation Method and Intelligence Evaluation Framework for Automated Vehicles
  19. On the Amplification of Linguistic Bias through Unintentional Self-reinforcement Learning by Generative Language Models -- A Perspective
  20. Collaborative Robotic Biopsy with Trajectory Guidance and Needle Tip Force Feedback
  21. Argumentative Characterizations of (Extended) Disjunctive Logic Programs
  22. On the Dynamics of Learning Time-Aware Behavior with Recurrent Neural Networks
  23. Diverse Projection Ensembles for Distributional Reinforcement Learning
  24. Analysis of the Relative Entropy Asymmetry in the Regularization of Empirical Risk Minimization
  25. Improving Forecasts for Heterogeneous Time Series by "Averaging", with Application to Food Demand Forecast
  26. On building machine learning pipelines for Android malware detection: a procedural survey of practices, challenges and opportunities
  27. Language of Bargaining
  28. Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call Center Corpus
  29. Coupled Attention Networks for Multivariate Time Series Anomaly Detection
  30. Linear Classifier: An Often-Forgotten Baseline for Text Classification
  31. Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning
  32. Unveiling the Hessian's Connection to the Decision Boundary
  33. Efficiently Learning the Graph for Semi-supervised Learning
  34. Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
  35. Topology Repairing of Disconnected Pulmonary Airways and Vessels: Baselines and a Dataset
  36. MaskedFusion360: Reconstruct LiDAR Data by Querying Camera Features
  37. LUT-GCE: Lookup Table Global Curve Estimation for Fast Low-light Image Enhancement
  38. Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence
  39. Using a neural network approach to accelerate disequilibrium chemistry calculations in exoplanet atmospheres
  40. Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals
  41. Deep Model Compression Also Helps Models Capture Ambiguity
  42. Prediction Algorithms Achieving Bayesian Decision Theoretical Optimality Based on Decision Trees as Data Observation Processes
  43. A Distribution Optimization Framework for Confidence Bounds of Risk Measures
  44. Kernel Random Projection Depth for Outlier Detection
  45. Gradient Ascent Post-training Enhances Language Model Generalization
  46. Imbalanced Multi-label Classification for Business-related Text with Moderately Large Label Spaces
  47. Data-Driven Bilateral Generalized Two-Dimensional Quaternion Principal Component Analysis with Application to Color Face Recognition
  48. Transformers learn through gradual rank increase
  49. Nonlinear SVD with Asymmetric Kernels: feature learning and asymmetric Nystr"om method
  50. Making Binary Classification from Multiple Unlabeled Datasets Almost Free of Supervision
  51. When Vision Fails: Text Attacks Against ViT and OCR
  52. Mitigating Prior Errors in Causal Structure Learning: A Resilient Approach via Bayesian Networks
  53. Resource Efficient Neural Networks Using Hessian Based Pruning
  54. Rotational augmentation techniques: a new perspective on ensemble learning for image classification
  55. DRCFS: Doubly Robust Causal Feature Selection
  56. Dynamic Causal Graph Convolutional Network for Traffic Prediction
  57. Combining Primal and Dual Representations in Deep Restricted Kernel Machines Classifiers
  58. Generating Language Corrections for Teaching Physical Control Tasks
  59. AI-Generated Image Detection using a Cross-Attention Enhanced Dual-Stream Network
  60. Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes
  61. Slot-VAE: Object-Centric Scene Generation with Slot Attention
  62. How robust accuracy suffers from certified training with convex relaxations
  63. Correlated Time Series Self-Supervised Representation Learning via Spatiotemporal Bootstrapping
  64. Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers with Partially Annotated Ultrasound Images
  65. A Weakly Supervised Approach to Emotion-change Prediction and Improved Mood Inference
  66. A Computational Theory and Semi-Supervised Algorithm for Clustering
  67. Viewpoint Generation using Feature-Based Constrained Spaces for Robot Vision Systems
  68. Can Forward Gradient Match Backpropagation?
  69. NF4 Isn't Information Theoretically Optimal (and that's Good)
  70. Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
  71. Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks
  72. A Brief Review of Hypernetworks in Deep Learning
  73. Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition
  74. Rethinking Translation Memory Augmented Neural Machine Translation
  75. Underwater Acoustic Target Recognition based on Smoothness-inducing Regularization and Spectrogram-based Data Augmentation
  76. The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues
  77. High-precision interpolation of stellar atmospheres with a deep neural network using a 1D convolutional auto encoder for feature extraction
  78. CARL-G: Clustering-Accelerated Representation Learning on Graphs
  79. LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Types
  80. Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs)
  81. Evolving Semantic Prototype Improves Generative Zero-Shot Learning
  82. Localised Adaptive Spatial-Temporal Graph Neural Network
  83. Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search
  84. TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI
  85. On the Viability of using LLMs for SW/HW Co-Design: An Example in Designing CiM DNN Accelerators
  86. Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
  87. The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation
  88. Enhancing COVID-19 Diagnosis through Vision Transformer-Based Analysis of Chest X-ray Images
  89. A Graph Transformer-Driven Approach for Network Robustness Learning
  90. Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience
  91. Active Learning Guided Fine-Tuning for enhancing Self-Supervised Based Multi-Label Classification of Remote Sensing Images
  92. Differentiable Multi-Fidelity Fusion: Efficient Learning of Physics Simulations with Neural Architecture Search and Transfer Learning
  93. Augmenting Zero-Shot Detection Training with Image Labels
  94. MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting
  95. A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
  96. In-context Cross-Density Adaptation on Noisy Mammogram Abnormalities Detection
  97. On the N-gram Approximation of Pre-trained Language Models
  98. NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection
  99. Unmasking Deepfakes: Masked Autoencoding Spatiotemporal Transformers for Enhanced Video Forgery Detection
  100. Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers
  101. History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
  102. Sticker820K: Empowering Interactive Retrieval with Stickers
  103. Generating Synthetic Datasets by Interpolating along Generalized Geodesics
  104. Deep denoising autoencoder-based non-invasive blood flow detection for arteriovenous fistula
  105. Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization
  106. Small Temperature is All You Need for Differentiable Architecture Search
  107. Rethink DARTS Search Space and Renovate a New Benchmark
  108. UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization
  109. Volume-DROID: A Real-Time Implementation of Volumetric Mapping with DROID-SLAM
  110. Mitigating Transformer Overconfidence via Lipschitz Regularization
  111. Information-Theoretic Limits and Strong Consistency on Binary Non-uniform Hypergraph Stochastic Block Models
  112. Provably Efficient Bayesian Optimization with Unknown Gaussian Process Hyperparameter Estimation
  113. Recurrent Attention Networks for Long-text Modeling
  114. AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
  115. Leveraging Skill-to-Skill Supervision for Knowledge Tracing
  116. Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
  117. When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset
  118. AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learning
  119. SE#PCFG: Semantically Enhanced PCFG for Password Analysis and Cracking
  120. Weakly supervised information extraction from inscrutable handwritten document images
  121. Towards end-to-end ASP computation
  122. Multimodal Audio-textual Architecture for Robust Spoken Language Understanding
  123. TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
  124. Particularity