mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 26 Jun 2023

204 papers

  1. Are aligned neural networks adversarially aligned?LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  2. Equivariant flow matchingDiffusion models → Flow matching, time series and science
  3. Large Multimodal Models: Notes on CVPR 2023 TutorialMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. Restart Sampling for Improving Generative ProcessesDiffusion models → Diffusion foundations and sampling
  5. Kosmos-2: Grounding Multimodal Large Language Models to the WorldMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  6. Accelerating Molecular Graph Neural Networks via Knowledge DistillationKnowledge distillation → Graph neural network distillation
  7. On Imitation in Mean-field GamesOffline RL and imitation learning from data → Inverse reinforcement learning
  8. Automatic Assessment of Divergent Thinking in Chinese Language with TransDis: A Transformer-Based Language Model ApproachLLM reasoning → Reasoning benchmarks and evaluation
  9. ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided DiffusionDiffusion models → Diffusion foundations and sampling
  10. ChiPFormer: Transferable Chip Placement via Offline Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
  11. DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  12. An Integral Projection-based Semantic Autoencoder for Zero-Shot LearningMechanistic interpretability → Interpreting vision and multimodal models
  13. SugarCrepe: Fixing Hackable Benchmarks for Vision-Language CompositionalityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  14. Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction TuningMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  15. A-STAR: Test-time Attention Segregation and Retention for Text-to-image SynthesisDiffusion models → Image generation, text-to-image and editing
  16. CEIL: Generalized Contextual Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  17. Data-Driven Approach for Formality-Sensitive Machine Translation: Language-Specific Handling and Synthetic Data GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  18. Design from Policies: Conservative Test-Time Adaptation for Offline Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms
  19. Knowledge Graph-Augmented Korean Generative Commonsense ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  20. Federated Learning on Non-iid Data via Local and Global DistillationKnowledge distillation → Federated, robust and private distillation
  21. DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image EditingDiffusion models → Image generation, text-to-image and editing
  22. Score-based Source Separation with Applications to Digital Communication SignalsDiffusion models → Audio, speech and music
  23. Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  24. Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer InferenceEfficient LLM inference and serving → Early exit and edge inference
  25. Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach
  26. Goal quest for an intelligent surfer moving in a chaotic flow
  27. A Food Recommender System in Academic Environments Based on Machine Learning Models
  28. A Collaborative Transfer Learning Framework for Cross-domain Recommendation
  29. Imitation with Spatial-Temporal Heatmap: 2nd Place Solution for NuPlan Challenge
  30. Procedural content generation of puzzle games using conditional generative adversarial networks
  31. Continual Learning for Out-of-Distribution Pedestrian Detection
  32. Transfer: Cross Modality Knowledge Transfer using Adversarial Networks -- A Study on Gesture Recognition
  33. FeedbackMap: a tool for making sense of open-ended survey responses
  34. Self-Supervised Image Captioning with CLIP
  35. Deep Transfer Learning for Intelligent Vehicle Perception: a Survey
  36. Structured Dialogue Discourse Parsing
  37. Off-Policy Evaluation of Ranking Policies under Diverse User Behavior
  38. C3S Micro-architectural Enhancement: Spike Encoder Block and Relaxing Gamma Clock (Asynchronous)
  39. Understanding In-Context Learning via Supportive Pretraining Data
  40. Energy Modelling and Forecasting for an Underground Agricultural Farm using a Higher Order Dynamic Mode Decomposition Approach
  41. WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models
  42. Balanced Filtering via Disclosure-Controlled Proxies
  43. A direct optimization algorithm for input-constrained MPC
  44. CLERA: A Unified Model for Joint Cognitive Load and Eye Region Analysis in the Wild
  45. Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression
  46. BatchGFN: Generative Flow Networks for Batch Active Learning
  47. Optimal Differentially Private Model Training with Public Data
  48. Action Anticipation with Goal Consistency
  49. Towards Sybil Resilience in Decentralized Learning
  50. Optimized Vectorizing of Building Structures with Switch: High-Efficiency Convolutional Channel-Switch Hybridization Strategy
  51. Beyond dynamic programming
  52. Scaling and Resizing Symmetry in Feedforward Networks
  53. Statistical Component Separation for Targeted Signal Recovery in Noisy Mixtures
  54. Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour Fields
  55. Spectral Analysis of Marine Debris in Simulated and Observed Sentinel-2/MSI Images using Unsupervised Classification
  56. Quality Issues in Machine Learning Software Systems
  57. DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome
  58. LM4HPC: Towards Effective Language Model Application in High-Performance Computing
  59. Fairness Aware Counterfactuals for Subgroups
  60. The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets
  61. On the Sample Complexity of Quantum Boltzmann Machine Learning
  62. SIMMF: Semantics-aware Interactive Multiagent Motion Forecasting for Autonomous Vehicle Driving
  63. The Art of Embedding Fusion: Optimizing Hate Speech Detection
  64. Minimum Description Length Clustering to Measure Meaningful Image Complexity
  65. Sciama's argument on life in a random universe: Distinguishing apples from oranges
  66. Integrating Bidirectional Long Short-Term Memory with Subword Embedding for Authorship Attribution
  67. GloptiNets: Scalable Non-Convex Optimization with Certificates
  68. FunQA: Towards Surprising Video Comprehension
  69. InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
  70. RVT: Robotic View Transformer for 3D Object Manipulation
  71. LongCoder: A Long-Range Pre-trained Language Model for Code Completion
  72. Supervised Pretraining Can Learn In-Context Reinforcement Learning
  73. Fuzzy-Conditioned Diffusion and Diffusion Projection Attention Applied to Facial Image Correction
  74. Learning to Modulate pre-trained Models in RL
  75. Domain-Scalable Unpaired Image Translation via Latent Space Anchoring
  76. A Fully Unsupervised Instance Segmentation Technique for White Blood Cell Images
  77. Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits
  78. Composing Parameter-Efficient Modules with Arithmetic Operations
  79. Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language
  80. Leveraging Task Structures for Improved Identifiability in Neural Network Representations
  81. Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories
  82. Proportional Aggregation of Preferences for Sequential Decision Making
  83. Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles
  84. CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation
  85. Efficient Cross-Validation for Sparse Linear Regression
  86. ViNT: A Foundation Model for Visual Navigation
  87. Building Flyweight FLIM-based CNNs with Adaptive Decoding for Object Detection
  88. Scalable Neural Contextual Bandit for Recommender Systems
  89. HonestBait: Forward References for Attractive but Faithful Headline Generation
  90. Vietnamese multi-document summary using subgraph selection approach -- VLSP 2022 AbMuSu Shared Task
  91. Label-Aware Hyperbolic Embeddings for Fine-grained Emotion Classification
  92. Black holes and the loss landscape in machine learning
  93. Experiments with Detecting and Mitigating AI Deception
  94. Probabilistic Risk Assessment of an Obstacle Detection System for GoA 4 Freight Trains
  95. MOVES: Movable and Moving LiDAR Scene Segmentation in Label-Free settings using Static Reconstruction
  96. Robust Wind Turbine Blade Segmentation from RGB Images in the Wild
  97. Tanimoto Random Features for Scalable Molecular Machine Learning
  98. Maximum State Entropy Exploration using Predecessor and Successor Representations
  99. A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling
  100. MotionGPT: Human Motion as a Foreign Language
All 204
  1. Segmentation of Industrial Burner Flames: A Comparative Study from Traditional Image Processing to Machine and Deep Learning
  2. Distributive Pre-Training of Generative Modeling Using Matrix-Product States
  3. INDEXITY: a web-based collaborative tool for medical video annotation
  4. Parameter-Level Soft-Masking for Continual Learning
  5. Uncovering Political Hate Speech During Indian Election Campaign: A New Low-Resource Dataset and Baselines
  6. PMaF: Deep Declarative Layers for Principal Matrix Features
  7. Repr'esentation graphique de la langue des signes franccaise et 'edition logicielle
  8. The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory
  9. MedLSAM: Localize and Segment Anything Model for 3D CT Images
  10. A denoised Mean Teacher for domain adaptive point cloud registration
  11. Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression
  12. Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection
  13. Error correcting 2D-3D cascaded network for myocardial infarct scar segmentation on late gadolinium enhancement cardiac magnetic resonance images
  14. FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering
  15. Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving
  16. A Simple and Effective Baseline for Attentional Generative Adversarial Networks
  17. Augmenting Control over Exploration Space in Molecular Dynamics Simulators to Streamline De Novo Analysis through Generative Control Policies
  18. Ontology Enrichment from Texts: A Biomedical Dataset for Concept Discovery and Placement
  19. Hard Sample Mining Enabled Supervised Contrastive Feature Learning for Wind Turbine Pitch System Fault Diagnosis
  20. How About Kind of Generating Hedges using End-to-End Neural Models?
  21. Dialectical Reconciliation via Structured Argumentative Dialogues
  22. Conformal link prediction for false discovery rate control
  23. An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics
  24. GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration
  25. Multi-Agent Deep Reinforcement Learning for Dynamic Avatar Migration in AIoT-enabled Vehicular Metaverses with Trajectory Prediction
  26. A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
  27. Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs
  28. PWSHAP: A Path-Wise Explanation Model for Targeted Variables
  29. Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
  30. Cross Architecture Distillation for Face Recognition
  31. Beyond AUROC & co. for evaluating out-of-distribution detection performance
  32. PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture
  33. Mono-to-stereo through parametric stereo generation
  34. Multi-View Attention Learning for Residual Disease Prediction of Ovarian Cancer
  35. PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas
  36. 3D-Aware Adversarial Makeup Generation for Facial Privacy Protection
  37. FeSViBS: Federated Split Learning of Vision Transformer with Block Sampling
  38. Localized Text-to-Image Generation for Free via Cross Attention Control
  39. JSEEGraph: Joint Structured Event Extraction as Graph Parsing
  40. Estimating player completion rate in mobile puzzle games using reinforcement learning
  41. Insights From Insurance for Fair Machine Learning
  42. Video object detection for privacy-preserving patient monitoring in intensive care
  43. Verification of Neural Network Control Systems using Symbolic Zonotopes and Polynotopes
  44. The race to robustness: exploiting fragile models for urban camouflage and the imperative for machine learning security
  45. Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems
  46. Multivariate Time Series Early Classification Across Channel and Time Dimensions
  47. Learning with Difference Attention for Visually Grounded Self-supervised Representations
  48. Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception
  49. Deep Learning for Cancer Prognosis Prediction Using Portrait Photos by StyleGAN Embedding
  50. Transfer Learning across Several Centuries: Machine and Historian Integrated Method to Decipher Royal Secretary's Diary
  51. CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformer
  52. Methodology for generating synthetic labeled datasets for visual container inspection
  53. Exploring the Robustness of Large Language Models for Solving Programming Problems
  54. TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
  55. U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoT
  56. Feature Imitating Networks Enhance The Performance, Reliability And Speed Of Deep Learning On Biomedical Image Processing Tasks
  57. Elucidating Interfacial Dynamics of Ti-Al Systems Using Molecular Dynamics Simulation and Markov State Modeling
  58. Multi-output Ensembles for Multi-step Forecasting
  59. Creating user stereotypes for persona development from qualitative data through semi-automatic subspace clustering
  60. logLTN: Differentiable Fuzzy Logic in the Logarithm Space
  61. Time and State Dependent Neural Delay Differential Equations
  62. Learnable Differencing Center for Nighttime Depth Perception
  63. About the Cost of Central Privacy in Density Estimation
  64. ParameterNet: Parameters Are All You Need
  65. Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning
  66. Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis
  67. Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition
  68. Optimizing Kernel-Target Alignment for cloud detection in multispectral satellite images
  69. TaylorPDENet: Learning PDEs from non-grid Data
  70. Deep Bayesian Experimental Design for Quantum Many-Body Systems
  71. AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor
  72. Practical Privacy-Preserving Gaussian Process Regression via Secret Sharing
  73. A Badminton Recognition and Tracking System Based on Context Multi-feature Fusion
  74. TaiChi Action Capture and Performance Analysis with Multi-view RGB Cameras
  75. Decentralized Multi-Robot Formation Control Using Reinforcement Learning
  76. Iterative-in-Iterative Super-Resolution Biomedical Imaging Using One Real Image
  77. Moving Avatars and Agents in Social Extended Reality Environments
  78. Medical Federated Model with Mixture of Personalized and Sharing Components
  79. STEF-DHNet: Spatiotemporal External Factors Based Deep Hybrid Network for Enhanced Long-Term Taxi Demand Prediction
  80. A General Framework for Sequential Decision-Making under Adaptivity Constraints
  81. Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation
  82. Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
  83. Histopathology Image Classification using Deep Manifold Contrastive Learning
  84. Fauno: The Italian Large Language Model that will leave you senza parole!
  85. Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
  86. Progressive Energy-Based Cooperative Learning for Multi-Domain Image-to-Image Translation
  87. Topology Estimation of Simulated 4D Image Data by Combining Downscaling and Convolutional Neural Networks
  88. A Self-supervised Contrastive Learning Method for Grasp Outcomes Prediction
  89. Enhanced multi-fidelity modelling for digital twin and uncertainty quantification
  90. The Singing Voice Conversion Challenge 2023
  91. A Preference-aware Meta-optimization Framework for Personalized Vehicle Energy Consumption Estimation
  92. A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference
  93. TCEIP: Text Condition Embedded Regression Network for Dental Implant Position Prediction
  94. Anomaly Detection with Score Distribution Discrimination
  95. Contrastive Multi-view Framework for Customer Lifetime Value Prediction
  96. Mutual Query Network for Multi-Modal Product Image Segmentation
  97. ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer
  98. Gradient Descent Converges Linearly for Logistic Regression on Separable Data
  99. Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction
  100. Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural Networks
  101. Transcending Traditional Boundaries: Leveraging Inter-Annotator Agreement (IAA) for Enhancing Data Management Operations (DMOps)
  102. Inter-Annotator Agreement in the Wild: Uncovering Its Emerging Roles and Considerations in Real-World Scenarios
  103. Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Prediction
  104. Few-Shot Continual Learning via Flat-to-Wide Approaches