mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 18 Sep 2023

259 papers

  1. Defending Against Alignment-Breaking Attacks via Robustly Aligned LLMLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  2. Stabilizing RLHF through Advantage Model and Selective RehearsalLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  3. One ACT Play: Single Demonstration Behavior Cloning with Action Chunking TransformersOffline RL and imitation learning from data → Imitation learning methods
  4. Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-FunctionsOffline RL and imitation learning from data → Decision transformers and sequence modeling
  5. Understanding Catastrophic Forgetting in Language Models via Implicit InferenceLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  6. Reasoning about the Unseen for Efficient Outdoor Object NavigationLLM reasoning → Spatial and embodied reasoning
  7. SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language FeedbackLLM reasoning → Reasoning benchmarks and evaluation
  9. Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE EcosystemEnd-to-end autonomous driving → Cooperative and V2X driving
  10. An Empirical Study of Scaling Instruct-Tuned Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. Distilling HuBERT with LSTMs via Decoupled Knowledge DistillationKnowledge distillation → Speech and audio distillation
  12. Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot AgentsLLM reasoning → Spatial and embodied reasoning +1
  13. Unsupervised Open-Vocabulary Object Localization in VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs
  14. RECAP: Retrieval-Augmented Audio CaptioningRetrieval-augmented generation → Multimodal RAG
  15. A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning TasksLLM reasoning → Multimodal reasoning
  16. DriveDreamer: Towards Real-world-driven World Models for Autonomous DrivingWorld models → World models for autonomous driving +1
  17. Privileged to Predicted: Towards Sensorimotor Reinforcement Learning for Urban DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
  18. Towards Socially Responsive Autonomous Vehicles: A Reinforcement Learning Framework with Driving Priors and Coordination AwarenessEnd-to-end autonomous driving → Cooperative and V2X driving
  19. Single and Few-step Diffusion for Generative Speech EnhancementDiffusion models → Audio, speech and music
  20. Gradpaint: Gradient-Guided Inpainting with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  21. Heterogeneous Generative Knowledge Distillation with Masked Image ModelingKnowledge distillation → General knowledge distillation methods
  22. Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story SynthesisDiffusion models → Image generation, text-to-image and editing
  23. Training dynamic models using early exits for automatic speech recognition on resource-constrained devicesEfficient LLM inference and serving → Early exit and edge inference
  24. Progressive Text-to-Image Diffusion with Soft Latent DirectionDiffusion models → Image generation, text-to-image and editing
  25. Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline DemonstrationOffline RL and imitation learning from data → Safe offline RL
  26. Towards Net-Zero Carbon Emissions in Network AI for 6G and Beyond
  27. Integration of Swin UNETR and statistical shape modeling for a semi-automated segmentation of the knee and biomechanical modeling of articular cartilage
  28. Interpretability is not Explainability: New Quantitative XAI Approach with a focus on Recommender Systems in Education
  29. Tree-Based Reconstructive Partitioning: A Novel Low-Data Level Generation Approach
  30. Machine Learning Technique Based Fake News Detection
  31. UNICON: A unified framework for behavior-based consumer segmentation in e-commerce
  32. Causal Discovery and Counterfactual Explanations for Personalized Student Learning
  33. Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach
  34. Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models
  35. Loop Polarity Analysis to Avoid Underspecification in Deep Learning
  36. ProtoKD: Learning from Extremely Scarce Data for Parasite Ova Recognition
  37. Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective
  38. Image-Text Pre-Training for Logo Recognition
  39. The Kernel Density Integral Transformation
  40. Stochastic Deep Koopman Model for Quality Propagation Analysis in Multistage Manufacturing Systems
  41. Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence
  42. QoS-Aware Service Prediction and Orchestration in Cloud-Network Integrated Beyond 5G
  43. Positive and Risky Message Assessment for Music Products
  44. Double Deep Q-Learning-based Path Selection and Service Placement for Latency-Sensitive Beyond 5G Applications
  45. Self-Sustaining Multiple Access with Continual Deep Reinforcement Learning for Dynamic Metaverse Applications
  46. Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach
  47. Specification-Driven Video Search via Foundation Models and Formal Verification
  48. Generative modeling, design and analysis of spider silk protein sequences for enhanced mechanical properties
  49. Few-Shot Adaptation for Parsing Contextual Utterances with LLMs
  50. A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops
  51. RadOnc-GPT: A Large Language Model for Radiation Oncology
  52. Offline Detection of Misspelled Handwritten Words by Convolving Recognition Model Features with Text Labels
  53. Autoencoder-based Anomaly Detection System for Online Data Quality Monitoring of the CMS Electromagnetic Calorimeter
  54. Preserving Tumor Volumes for Unsupervised Medical Image Registration
  55. Analysis of the Memorization and Generalization Capabilities of AI Agents: Are Continual Learners Robust?
  56. Realistic Website Fingerprinting By Augmenting Network Trace
  57. Human Gait Recognition using Deep Learning: A Comprehensive Review
  58. Neural Feature Learning in Function Space
  59. Efficient Low-Rank GNN Defense Against Structural Attacks
  60. GDM: Dual Mixup for Graph Classification with Limited Supervision
  61. Deep Prompt Tuning for Graph Transformers
  62. Adaptive Liquidity Provision in Uniswap V3 with Deep Reinforcement Learning
  63. Pre-training on Synthetic Driving Data for Trajectory Prediction
  64. Deep smoothness WENO scheme for two-dimensional hyperbolic conservation laws: A deep learning approach for learning smoothness indicators
  65. AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation
  66. A Semi-Supervised Approach for Power System Event Identification
  67. Data Formulator: AI-powered Concept-driven Visualization Authoring
  68. Conformal Temporal Logic Planning using Large Language Models
  69. Unified Coarse-to-Fine Alignment for Video-Text Retrieval
  70. HTEC: Human Transcription Error Correction
  71. Invariant Probabilistic Prediction
  72. GAME: Generalized deep learning model towards multimodal data integration for early screening of adolescent mental disorders
  73. Sex-based Disparities in Brain Aging: A Focus on Parkinson's Disease
  74. A Unifying Perspective on Non-Stationary Kernels for Deeper Gaussian Processes
  75. Automatic Personalized Impression Generation for PET Reports Using Large Language Models
  76. Toward collision-free trajectory for autonomous and pilot-controlled unmanned aerial vehicles
  77. Survey of Consciousness Theory from Computational Perspective
  78. Dual Student Networks for Data-Free Model Stealing
  79. Hierarchy Builder: Organizing Textual Spans into a Hierarchy to Facilitate Navigation
  80. A Modular Spatial Clustering Algorithm with Noise Specification
  81. Multimodal Foundation Models: From Specialists to General-Purpose Assistants
  82. Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
  83. Evaluation of GPT-3 for Anti-Cancer Drug Sensitivity Prediction
  84. Prognosis of Multivariate Battery State of Performance and Health via Transformers
  85. Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin
  86. Looking through the past: better knowledge retention for generative replay in continual learning
  87. Universal Photorealistic Style Transfer: A Lightweight and Adaptive Approach
  88. Machine Learning Approaches to Predict and Detect Early-Onset of Digital Dermatitis in Dairy Cows using Sensor Data
  89. DeepHEN: quantitative prediction essential lncRNA genes and rethinking essentialities of lncRNA genes
  90. The Optimized path for the public transportation of Incheon in South Korea
  91. General In-Hand Object Rotation with Vision and Touch
  92. A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning
  93. Des-q: a quantum algorithm to provably speedup retraining of decision trees
  94. GEDepth: Ground Embedding for Monocular Depth Estimation
  95. MindAgent: Emergent Gaming Interaction
  96. Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data
  97. Prompt a Robot to Walk with Large Language Models
  98. Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
  99. vSHARP: variable Splitting Half-quadratic Admm algorithm for Reconstruction of inverse-Problems
  100. How to Generate Popular Post Headlines on Social Media?
All 259
  1. Deep Visual Odometry with Events and Frames
  2. DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models
  3. Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation
  4. Evaluating Adversarial Robustness with Expected Viable Performance
  5. DYMAG: Rethinking Message Passing Using Dynamical-systems-based Waveforms
  6. A Heterogeneous Graph-Based Multi-Task Learning for Fault Event Diagnosis in Smart Grid
  7. Evaluation of Human-Understandability of Global Model Explanations using Decision Tree
  8. Learning Nonparametric High-Dimensional Generative Models: The Empirical-Beta-Copula Autoencoder
  9. Wait, That Feels Familiar: Learning to Extrapolate Human Preferences for Preference Aligned Path Planning
  10. Quantum Vision Clustering
  11. Learning Generative Models for Lumped Rainfall-Runoff Modeling
  12. Speaker attribution in German parliamentary debates with QLoRA-adapted large language models
  13. The role of causality in explainable artificial intelligence
  14. Towards Ontology Construction with Language Models
  15. Walking fingerprinting
  16. Context is Environment
  17. On Model Explanations with Transferable Neural Pathways
  18. Deep Reinforcement Learning for the Joint Control of Traffic Light Signaling and Vehicle Speed Advice
  19. Error Reduction from Stacked Regressions
  20. Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Texts
  21. RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps
  22. EGFE: End-to-end Grouping of Fragmented Elements in UI Designs with Multimodal Learning
  23. Domain Generalization with Fourier Transform and Soft Thresholding
  24. Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight
  25. Learning Spatial and Temporal Hierarchies: Hierarchical Active Inference for navigation in Multi-Room Maze Environments
  26. PseudoCal: Towards Initialisation-Free Deep Learning-Based Camera-LiDAR Self-Calibration
  27. CC-SGG: Corner Case Scenario Generation using Learned Scene Graphs
  28. Instruction-Following Speech Recognition
  29. HypR: A comprehensive study for ASR hypothesis revising with a reference corpus
  30. Task Selection and Assignment for Multi-modal Multi-task Dialogue Act Classification with Non-stationary Multi-armed Bandits
  31. Pivotal Estimation of Linear Discriminant Analysis in High Dimensions
  32. Clustering of Urban Traffic Patterns by K-Means and Dynamic Time Warping: Case Study
  33. Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding
  34. Bias of AI-Generated Content: An Examination of News Produced by Large Language Models
  35. Grasp-Anything: Large-scale Grasp Dataset from Foundation Models
  36. Convolutional Deep Kernel Machines
  37. R2GenGPT: Radiology Report Generation with Frozen LLMs
  38. Efficient Concept Drift Handling for Batch Android Malware Detection Models
  39. Learning Optimal Contracts: How to Exploit Small Action Spaces
  40. AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification
  41. Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
  42. Harnessing Collective Intelligence Under a Lack of Cultural Consensus
  43. The ParlaSent Multilingual Training Dataset for Sentiment Identification in Parliamentary Proceedings
  44. Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning
  45. Semantically Redundant Training Data Removal and Deep Model Classification Performance: A Study with Chest X-rays
  46. How to Data in Datathons
  47. Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections
  48. Application-driven Validation of Posteriors in Inverse Problems
  49. Contrastive Initial State Buffer for Reinforcement Learning
  50. Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge Distillation
  51. Towards Better Modeling with Missing Data: A Contrastive Learning-based Visual Analytics Perspective
  52. The NFLikelihood: an unsupervised DNNLikelihood from Normalizing Flows
  53. Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels
  54. Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints
  55. RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud
  56. An Optimization Case Study for solving a Transport Robot Scheduling Problem on Quantum-Hybrid and Quantum-Inspired Hardware
  57. Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representation
  58. Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency
  59. When Large Language Models Meet Citation: A Survey
  60. Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data
  61. Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering
  62. Traffic Scene Similarity: a Graph-based Contrastive Learning Approach
  63. FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data
  64. Multi-Dictionary Tensor Decomposition
  65. Dealing with negative samples with multi-task learning on span-based joint entity-relation extraction
  66. CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation
  67. LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models
  68. Information based explanation methods for deep learning agents -- with applications on large open-source chess models
  69. Securing Fixed Neural Network Steganography
  70. A Study of Data-driven Methods for Adaptive Forecasting of COVID-19 Cases
  71. Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels
  72. Noise-Augmented Boruta: The Neural Network Perturbation Infusion with Boruta Feature Selection
  73. Do learned speech symbols follow Zipf's law?
  74. Ugly Ducklings or Swans: A Tiered Quadruplet Network with Patient-Specific Mining for Improved Skin Lesion Classification
  75. Distributed course allocation with asymmetric friendships
  76. Conditioning Latent-Space Clusters for Real-World Anomaly Classification
  77. DGM-DR: Domain Generalization with Mutual Information Regularized Diabetic Retinopathy Classification
  78. DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
  79. Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation
  80. Multi-turn Dialogue Comprehension from a Topic-aware Perspective
  81. A Novel Method of Fuzzy Topic Modeling based on Transformer Processing
  82. Speech Synthesis By Unrolling Diffusion Process using Neural Network Layers
  83. VULNERLIZER: Cross-analysis Between Vulnerabilities and Software Libraries
  84. HiT: Building Mapping with Hierarchical Transformers
  85. Neural Network-Based Rule Models With Truth Tables
  86. Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation
  87. Holistic Geometric Feature Learning for Structured Reconstruction
  88. A Discussion on Generalization in Next-Activity Prediction
  89. Collaborative Three-Stream Transformers for Video Captioning
  90. Proposition from the Perspective of Chinese Language: A Chinese Proposition Classification Evaluation Benchmark
  91. MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep Learning
  92. Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edge
  93. Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition
  94. An Autonomous Vision-Based Algorithm for Interplanetary Navigation
  95. Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
  96. Latent assimilation with implicit neural representations for unknown dynamics
  97. New Bounds on the Accuracy of Majority Voting for Multi-Class Classification
  98. RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy
  99. Summarization is (Almost) Dead
  100. Multi-dimensional domain generalization with low-rank structures
  101. A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting
  102. Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networks
  103. Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata
  104. Quantum Wasserstein GANs for State Preparation at Unseen Points of a Phase Diagram
  105. Towards a performance characteristic curve for model evaluation: an application in information diffusion prediction
  106. Selective Volume Mixup for Video Action Recognition
  107. Decompose Semantic Shifts for Composed Image Retrieval
  108. Adapting Large Language Models to Domains via Reading Comprehension
  109. DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues
  110. Improved Factorized Neural Transducer Model For text-only Domain Adaptation
  111. NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarios
  112. FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks
  113. Sparse and Privacy-enhanced Representation for Human Pose Estimation
  114. PanoMixSwap Panorama Mixing via Structural Swapping for Indoor Scene Understanding
  115. Learning Parallax for Stereo Event-based Motion Deblurring
  116. Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech
  117. Understanding Divergent Framing of the Supreme Court Controversies: Social Media vs. News Outlets
  118. Pruning Large Language Models via Accuracy Predictor
  119. LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
  120. Outlier-Insensitive Kalman Filtering: Theory and Applications
  121. RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision
  122. Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation
  123. PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction
  124. Search and Learning for Unsupervised Text Generation
  125. CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval
  126. HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
  127. Target-aware Bi-Transformer for Few-shot Segmentation
  128. Self-supervised TransUNet for Ultrasound regional segmentation of the distal radius in children
  129. Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing
  130. An Accurate and Efficient Neural Network for OCTA Vessel Segmentation and a New Dataset
  131. Spatio-temporal Co-attention Fusion Network for Video Splicing Localization
  132. Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization
  133. Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules
  134. Self-supervised Multi-view Clustering in Computer Vision: A Survey
  135. Reconstructing Existing Levels through Level Inpainting
  136. Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment
  137. Active anomaly detection based on deep one-class classification
  138. Reducing Adversarial Training Cost with Gradient Approximation
  139. Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles
  140. Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection
  141. CaT: Balanced Continual Graph Learning with Graph Condensation
  142. Asymptotically efficient adaptive identification under saturated output observation
  143. Are You Worthy of My Trust?: A Socioethical Perspective on the Impacts of Trustworthy AI Systems on the Environment and Human Society
  144. Scalable Label-efficient Footpath Network Generation Using Remote Sensing Data and Self-supervised Learning
  145. Investigating Zero- and Few-shot Generalization in Fact Verification
  146. Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
  147. On the Use of the Kantorovich-Rubinstein Distance for Dimensionality Reduction
  148. A Schedule of Duties in the Cloud Space Using a Modified Salp Swarm Algorithm
  149. An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
  150. FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining
  151. TransTouch: Learning Transparent Objects Depth Sensing Through Sparse Touches
  152. Joint Demosaicing and Denoising with Double Deep Image Priors
  153. Causal Discovery and Prediction: Methods and Algorithms
  154. Cross-attention-based saliency inference for predicting cancer metastasis on whole slide images
  155. Distributionally Time-Varying Online Stochastic Optimization under Polyak-Lojasiewicz Condition with Application in Conditional Value-at-Risk Statistical Learning
  156. BRONCO: Automated modelling of the bronchovascular bundle using the Computed Tomography Images
  157. Does Video Summarization Require Videos? Quantifying the Effectiveness of Language in Video Summarization
  158. Promoting Research Collaboration with Open Data Driven Team Recommendation in Response to Call for Proposals
  159. Selecting which Dense Retriever to use for Zero-Shot Search