mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 12 Apr 2024

220 papers

  1. A Review of Reward Functions for Reinforcement Learning in the context of Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  2. LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task AutomationLLM agents and tool use → GUI and mobile agents
  3. FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  4. WROOM: An Autonomous Driving Approach for Off-Road NavigationEnd-to-end autonomous driving → Reinforcement learning for driving +1
  5. Hindsight PRIORs for Reward Learning from Human PreferencesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  6. "Don't forget to put the milk back!" Dataset for Enabling Embodied Agents to Detect Anomalous SituationsLLM agents and tool use → Agent threats, guardrails and governance
  7. Semantic Approach to Quantifying the Consistency of Diffusion Model Image GenerationDiffusion models → Diffusion foundations and sampling
  8. Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System ModelsDiffusion models → Flow matching, time series and science
  9. The Elephant in the Room: Rethinking the Usage of Pre-trained Language Model in Sequential RecommendationLLM reasoning → LLM reasoning for recommendation
  10. JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language ModelsLLM safety and security → Jailbreaking
  11. Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation MismatchLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  12. LLM-Seg: Bridging Image Segmentation and Large Language Model ReasoningLLM reasoning → Multimodal reasoning
  13. Training a Vision Language Model as Smartphone AssistantMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation ModelsLLM safety and security → Backdoor and data poisoning attacks
  15. Lossy Image Compression with Foundation Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  16. Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario GenerationEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  17. RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  18. Advancing Forest Fire Prevention: Deep Reinforcement Learning for Effective Firebreak PlacementDeep reinforcement learning methods → RL for energy, networks and operations
  19. Adversarial Imitation Learning via BoostingOffline RL and imitation learning from data → Imitation learning methods +1
  20. Efficient Interactive LLM Serving with Proxy Model-based Sequence Length PredictionEfficient LLM inference and serving → Serving systems and request scheduling
  21. Prescribing Optimal Health-Aware Operation for Urban Air Mobility with Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  22. Dataset Reset Policy Optimization for RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  23. Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-DistillationKnowledge distillation → Knowledge distillation for LLMs
  24. SpectralMamba: Efficient Mamba for Hyperspectral Image ClassificationState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  25. MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery DetectionMixture-of-experts → Vision mixture-of-experts
  26. SIR-RL: Reinforcement Learning for Optimized Policy Control during Epidemiological Outbreaks in Emerging Market and Developing EconomiesDeep reinforcement learning methods → RL for clinical treatment and surgery
  27. PiRD: Physics-informed Residual Diffusion for Flow Field ReconstructionDiffusion models → Flow matching, time series and science
  28. MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image FusionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  29. A Complexity Map of Probabilistic Reasoning for Neurosymbolic Classification TechniquesLLM reasoning → Reasoning benchmarks and evaluation
  30. Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You ThinkLLM reasoning → Reasoning benchmarks and evaluation
  31. TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot AbilityDeep reinforcement learning methods → RL for robot navigation and UAV control
  32. Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak AttemptsLLM safety and security → Jailbreaking
  33. Struggle with Adversarial Defense? Try DiffusionDiffusion models → Robustness, privacy and adversarial aspects
  34. Guided Masked Self-Distillation Modeling for Distributed Multimedia Sensor Event AnalysisKnowledge distillation → Detection and dense prediction distillation
  35. Balanced Mixed-Type Tabular Data Synthesis with Diffusion ModelsDiffusion models → Flow matching, time series and science +1
  36. Agile and versatile bipedal robot tracking control through reinforcement learningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  37. RLEMMO: Evolutionary Multimodal Optimization Assisted By Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  38. Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  39. Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  40. Improving Continuous Sign Language Recognition with Adapted Image ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  41. Reducing hallucination in structured outputs via Retrieval-Augmented GenerationRetrieval-augmented generation → Hallucination detection in RAG
  42. AIMDiT: Modality Augmentation and Interaction via Multimodal Dimension Transformation for Emotion Recognition in Conversations
  43. Artificial Intelligence in Everyday Life 2.0: Educating University Students from Different Majors
  44. D2E-An Autonomous Decision-making Dataset involving Driver States and Human Evaluation
  45. A Cloud-Edge Framework for Energy-Efficient Event-Driven Control: An Integration of Online Supervised Learning, Spiking Neural Networks and Local Plasticity Rules
  46. Deep Learning for Educational Data Science
  47. A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications
  48. Mitigating Cascading Effects in Large Adversarial Graph Environments
  49. PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis
  50. The Path To Autonomous Cyber Defense
  51. SEVD: Synthetic Event-based Vision Dataset for Ego and Fixed Traffic Perception
  52. Into the Fog: Evaluating Robustness of Multiple Object Tracking
  53. Kinematics Modeling of Peroxy Free Radicals: A Deep Reinforcement Learning Approach
  54. Uncertainty Quantification in Detecting Choroidal Metastases on MRI via Evolutionary Strategies
  55. Assessing Economic Viability: A Comparative Analysis of Total Cost of Ownership for Domain-Adapted Large Language Models versus State-of-the-art Counterparts in Chip Design Coding Assistance
  56. LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
  57. Experimental Design for Active Transductive Inference in Large Language Models
  58. ContactDexNet: Multi-fingered Robotic Hand Grasping in Cluttered Environments through Hand-object Contact Semantic Mapping
  59. Multiply-Robust Causal Change Attribution
  60. Predicting Traffic Congestion at Urban Intersections Using Data-Driven Modeling
  61. Vehicle-to-Vehicle Charging: Model, Complexity, and Heuristics
  62. BERT-LSH: Reducing Absolute Compute For Attention
  63. Structured Model Pruning for Efficient Inference in Computational Pathology
  64. Measuring the Predictability of Recommender Systems using Structural Complexity Metrics
  65. Inverse Kinematics for Neuro-Robotic Grasping with Humanoid Embodied Agents
  66. Constrained C-Test Generation via Mixed-Integer Programming
  67. Single-image driven 3d viewpoint training data augmentation for effective wine label recognition
  68. The Illusion of State in State-Space Models
  69. Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance
  70. Measuring the Quality of Answers in Political Q&As with Large Language Models
  71. E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data
  72. Reducing the Barriers to Entry for Foundation Model Training
  73. Leveraging viscous Hamilton-Jacobi PDEs for uncertainty quantification in scientific machine learning
  74. CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation
  75. Real-time guidewire tracking and segmentation in intraoperative x-ray
  76. Random walks on simplicial complexes
  77. Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
  78. Convergence of coordinate ascent variational inference for log-concave measures via optimal transport
  79. Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes
  80. Detecting AI-Generated Images via CLIP
  81. NeuroLGP-SM: Scalable Surrogate-Assisted Neuroevolution for Deep Neural Networks
  82. Under pressure: learning-based analog gauge reading in the wild
  83. Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset
  84. CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models
  85. `Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
  86. The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Models
  87. SCOUT+: Towards Practical Task-Driven Drivers' Gaze Prediction
  88. Computing distances and means on manifolds with a metric-constrained Eikonal approach
  89. FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discrimination
  90. Data Limitations for Modeling Top-Down Effects on Drivers' Attention
  91. Multibranch Generative Models for Multichannel Imaging with an Application to PET/CT Synergistic Reconstruction
  92. Observation-specific explanations through scattered data approximation
  93. Can LLMs substitute SQL? Comparing Resource Utilization of Querying LLMs versus Traditional Relational Databases
  94. An Integrated Toolbox for Creating Neuromorphic Edge Applications
  95. VADA: a Data-Driven Simulator for Nanopore Sequencing
  96. Beyond One-Size-Fits-All: Adapting Counterfactual Explanations to User Objectives
  97. Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification
  98. State-space systems as dynamic generative models
  99. Differentially Private Log-Location-Scale Regression Using Functional Mechanism
  100. EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams
All 220
  1. COCONut: Modernizing COCO Segmentation
  2. Probing the 3D Awareness of Visual Foundation Models
  3. When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
  4. A Conceptual Framework for Conversational Search and Recommendation: Conceptualizing Agent-Human Interactions During the Conversational Search Process
  5. Is ChatGPT Transforming Academics' Writing Style?
  6. Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
  7. Synthetic Dataset Creation and Fine-Tuning of Transformer Models for Question Answering in Serbian
  8. Using Explainable AI and Transfer Learning to understand and predict the maintenance of Atlantic blocking with limited observational data
  9. Automatic Quantification of Serial PET/CT Images for Pediatric Hodgkin Lymphoma Patients Using a Longitudinally-Aware Segmentation Network
  10. Hyperbolic Delaunay Geometric Alignment
  11. Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
  12. Sliding down the stairs: how correlated latent variables accelerate learning with neural networks
  13. Generating Synthetic Time Series Data for Cyber-Physical Systems
  14. Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding
  15. Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts
  16. Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion
  17. Pathological Primitive Segmentation Based on Visual Foundation Model with Zero-Shot Mask Generation
  18. FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation
  19. Small Models Are (Still) Effective Cross-Domain Argument Extractors
  20. Mitigating Receiver Impact on Radio Frequency Fingerprint Identification via Domain Adaptation
  21. IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic
  22. MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking
  23. Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data
  24. Practical Guidelines for Cell Segmentation Models Under Optical Aberrations in Microscopy
  25. Analyzing Decades-Long Environmental Changes in Namibia Using Archival Aerial Photography and Deep Learning
  26. Memory Traces: Are Transformers Tulving Machines?
  27. On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation
  28. VertAttack: Taking advantage of Text Classifiers' horizontal vision
  29. Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking
  30. Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection
  31. Masked Image Modeling as a Framework for Self-Supervised Learning across Eye Movements
  32. Fuxi-DA: A Generalized Deep Learning Data Assimilation Framework for Assimilating Satellite Observations
  33. Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward
  34. ChatGPT and general-purpose AI count fruits in pictures surprisingly well
  35. NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset
  36. Leveraging Multi-AI Agents for Cross-Domain Knowledge Discovery
  37. LaSagnA: Language-based Segmentation Assistant for Complex Queries
  38. 3D Human Scan With A Moving Event Camera
  39. Analyzing and Overcoming Local Optima in Complex Multi-Objective Optimization by Decomposition-Based Evolutionary Algorithms
  40. Thematic Analysis with Large Language Models: does it work with languages other than English? A targeted test in Italian
  41. Semantic Communication for Cooperative Multi-Task Processing over Wireless Networks
  42. Using ChatGPT for Data Science Analyses
  43. New Efficient Visual OILU Markers
  44. Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
  45. TSLANet: Rethinking Transformers for Time Series Representation Learning
  46. OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
  47. On the Independence Assumption in Neurosymbolic Learning
  48. A backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations
  49. Lightweight Multi-System Multivariate Interconnection and Divergence Discovery
  50. Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues
  51. OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering
  52. Federated Optimization with Doubly Regularized Drift Correction
  53. Anti-Byzantine Attacks Enabled Vehicle Selection for Asynchronous Federated Learning in Vehicular Edge Computing
  54. An improved tabular data generator with VAE-GMM integration
  55. MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition
  56. Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task
  57. Adapting the Segment Anything Model During Usage in Novel Situations
  58. Direct May Not Be the Best: An Incremental Evolution View of Pose Generation
  59. AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees
  60. Evolutionary Preference Sampling for Pareto Set Learning
  61. Seismic First Break Picking in a Higher Dimension Using Deep Graph Learning
  62. Learning representations of learning representations
  63. PnLCalib: Sports Field Registration via Points and Lines Optimization
  64. Mitigating Challenges of the Space Environment for Onboard Artificial Intelligence: Design Overview of the Imaging Payload on SpIRIT
  65. Multi-Agent eXperimenter (MAX)
  66. Data-Driven Preference Sampling for Pareto Front Learning
  67. NC-TTT: A Noise Contrastive Approach for Test-Time Training
  68. Graph data augmentation with Gromow-Wasserstein Barycenters
  69. Automatic Speech Recognition Advancements for Indigenous Languages of the Americas
  70. Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
  71. Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework
  72. Improving Health Question Answering with Reliable and Time-Aware Evidence Retrieval
  73. PMB5: Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks
  74. OmniSat: Self-Supervised Modality Fusion for Earth Observation
  75. Self-Supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representation
  76. Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks
  77. FastSpell: the LangId Magic Spell
  78. Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
  79. Toward a Theory of Tokenization in LLMs
  80. Emerging Property of Masked Token for Effective Pre-training
  81. Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
  82. Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Data
  83. BOND: Bootstrapping From-Scratch Name Disambiguation with Multi-task Promoting
  84. Multi-Step Traffic Prediction for Multi-Period Planning in Optical Networks
  85. The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing
  86. GPN: Generative Point-based NeRF
  87. A Large Scale Survey of Motivation in Software Development and Analysis of its Validity
  88. Collaborative-Enhanced Prediction of Spending on Newly Downloaded Mobile Games under Consumption Uncertainty
  89. Interference Motion Removal for Doppler Radar Vital Sign Detection Using Variational Encoder-Decoder Neural Network
  90. Study of Emotion Concept Formation by Integrating Vision, Physiology, and Word Information using Multilayered Multimodal Latent Dirichlet Allocation
  91. Overcoming Scene Context Constraints for Object Detection in wild using Defilters
  92. AdaContour: Adaptive Contour Descriptor with Hierarchical Representation
  93. On Input Formats for Radar Micro-Doppler Signature Processing by Convolutional Neural Networks
  94. A Survey of Neural Network Robustness Assessment in Image Recognition
  95. Calibration & Reconstruction: Deep Integrated Language for Referring Image Segmentation
  96. Convolutional neural network classification of cancer cytopathology images: taking breast cancer as an example
  97. Minimax Optimal Goodness-of-Fit Testing with Kernel Stein Discrepancy
  98. FaceFilterSense: A Filter-Resistant Face Recognition and Facial Attribute Analysis Framework
  99. Transfer Learning Study of Motion Transformer-based Trajectory Predictions
  100. Relational Prompt-based Pre-trained Language Models for Social Event Detection
  101. Pretraining and Updates of Domain-Specific LLM: A Case Study in the Japanese Business Domain
  102. Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study
  103. Practical Region-level Attack against Segment Anything Models
  104. MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance
  105. Simulation of a Vision Correction Display System
  106. IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer
  107. Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimality
  108. Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis
  109. HCL-MTSAD: Hierarchical Contrastive Consistency Learning for Accurate Detection of Industrial Multivariate Time Series Anomalies
  110. A Mutual Inclusion Mechanism for Precise Boundary Segmentation in Medical Images
  111. Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
  112. Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
  113. Measuring Cross-lingual Transfer in Bytes
  114. Adapting CNNs for Fisheye Cameras without Retraining
  115. Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similarity
  116. Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation
  117. Introducing Graph Learning over Polytopic Uncertain Graph
  118. Optimal Universal Quantum Encoding for Statistical Inference
  119. Conformal Prediction via Regression-as-Classification
  120. Language Model Prompt Selection via Simulation Optimization