mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 24 Jul 2024

229 papers

  1. PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute ControlDiffusion models → Image generation, text-to-image and editing
  2. Building a Domain-specific Guardrail Model in ProductionLLM safety and security → Safety alignment, refusal and guardrails
  3. Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical ApplicationsRetrieval-augmented generation → Medical and biomedical RAG
  4. Sentiment Reasoning for HealthcareLLM reasoning → Audio-language model reasoning
  5. Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership InferenceLLM safety and security → Membership inference attacks
  6. IgnitionInnovators at "Discharge Me!": Chain-of-Thought Instruction Finetuning Large Language Models for Discharge SummariesLLM reasoning → Clinical and biomedical applications
  7. Diffusion Models For Multi-Modal Generative ModelingDiffusion models → Image generation, text-to-image and editing
  8. Exploring Domain Robust Lightweight Reward Models based on Router MechanismLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  9. MathViz-E: A Case-study in Domain-Specialized Tool-Using AgentsLLM agents and tool use → Educational agents and math problem solving
  10. LAMBDA: A Large Model Based Data AgentLLM agents and tool use → Web, search, and research agents
  11. SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View ConsistencyDiffusion models → 3D, point cloud and scene generation
  12. Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  13. SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  14. VILA2: VILA Augmented VILAMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  15. FLRT: Fluent Student-Teacher RedteamingLLM safety and security → Prompt injection and agent security
  16. Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?LLM safety and security → Watermarking generated content and models
  17. PERSONA: A Reproducible Testbed for Pluralistic AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  18. MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. Boosting Large Language Models with Socratic Method for Conversational Mathematics TeachingLLM reasoning → Mathematical reasoning
  20. MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
  21. How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
  22. M4: Multi-Proxy Multi-Gate Mixture of Experts Network for Multiple Instance Learning in Histopathology Image AnalysisMixture-of-experts → Medical and biomedical MoE
  23. Pretrained Visual Representations in Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  24. LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN proverLLM reasoning → Mathematical reasoning
  25. Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning ProblemsDeep reinforcement learning methods → RL theory and sample complexity
  26. Testing Large Language Models on Driving Theory Knowledge and Skills for Connected Autonomous VehiclesEnd-to-end autonomous driving → Large language models for driving
  27. Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion ModelDiffusion models → Inverse problems and image restoration
  28. Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning ApproachDeep reinforcement learning methods → RL for robot locomotion and manipulation
  29. To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under AmbiguityLLM reasoning → Reasoning benchmarks and evaluation
  30. Neural Dueling Bandits: Preference-Based Optimization with Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  31. MemBench: Memorized Image Trigger Prompt Dataset for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  32. AI-Gadget Kit: Integrating Swarm User Interfaces with LLM-driven Agents for Rich Tabletop Game ApplicationsLLM agents and tool use → Reinforcement learning for LLM agents
  33. High Efficiency Image Compression for Large Visual-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  34. Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational InferenceDiffusion models → Diffusion foundations and sampling
  35. Gymnasium: A Standard Interface for Reinforcement Learning EnvironmentsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  36. Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention PerspectiveLLM safety and security → Machine unlearning
  37. Diffree: Text-Guided Shape Free Object Inpainting with Diffusion ModelDiffusion models → 3D, point cloud and scene generation
  38. Selective Vision-Language Subspace Projection for Few-shot CLIPMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  39. Towards Aligning Language Models with Textual FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  40. Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias MitigationLLM safety and security → Safety alignment, refusal and guardrails
  41. ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question AnsweringLLM reasoning → Clinical and biomedical applications
  42. SAR to Optical Image Translation with Color Supervised Diffusion ModelDiffusion models → Inverse problems and image restoration
  43. Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral CloningOffline RL and imitation learning from data → Imitation learning methods
  44. Using Large Language Models to Compare Explainable Models for Smart Home Human Activity Recognition
  45. Predicting cognitive load in immersive driving scenarios with a hybrid CNN-RNN model
  46. Amman City, Jordan: Toward a Sustainable City from the Ground Up
  47. Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge
  48. What Matters in Explanations: Towards Explainable Fake Review Detection Focusing on Transformers
  49. Utilizing Generative Adversarial Networks for Image Data Augmentation and Classification of Semiconductor Wafer Dicing Induced Defects
  50. A Large Encoder-Decoder Family of Foundation Models For Chemical Language
  51. Accelerating the Low-Rank Decomposed Models
  52. COEFF-KANs: A Paradigm to Address the Electrolyte Field with KANs
  53. An Efficient and Flexible Deep Learning Method for Signal Delineation via Keypoints Estimation
  54. Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC
  55. Online Social Network Data-Driven Early Detection on Short-Form Video Addiction
  56. Struc2mapGAN: improving synthetic cryo-EM density maps with generative adversarial networks
  57. CRASAR-U-DROIDs: A Large Scale Benchmark Dataset for Building Alignment and Damage Assessment in Georectified sUAS Imagery
  58. Spiking Neural Networks in Vertical Federated Learning: Performance Trade-offs
  59. Unsqueeze [CLS] Bottleneck to Learn Rich Representations
  60. Tackling the Problem of Distributional Shifts: Correcting Misspecified, High-Dimensional Data-Driven Priors for Inverse Problems
  61. SDLNet: Statistical Deep Learning Network for Co-Occurring Object Detection and Identification
  62. Generative Learning for Simulation of Vehicle Faults
  63. Hopfield Networks for Asset Allocation
  64. SMA-Hyper: Spatiotemporal Multi-View Fusion Hypergraph Learning for Traffic Accident Prediction
  65. Time Matters: Examine Temporal Effects on Biomedical Language Models
  66. BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning
  67. Revising the Problem of Partial Labels from the Perspective of CNNs' Robustness
  68. Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers
  69. PEEKABOO: Hiding parts of an image for unsupervised object localization
  70. Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs
  71. SAfEPaTh: A System-Level Approach for Efficient Power and Thermal Estimation of Convolutional Neural Network Accelerator
  72. Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
  73. CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis
  74. Pretraining a Neural Operator in Lower Dimensions
  75. Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networks
  76. Coupling Speech Encoders with Downstream Text Models
  77. Quality Assured: Rethinking Annotation Strategies in Imaging AI
  78. CityX: Controllable Procedural Content Generation for Unbounded 3D Cities
  79. Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning
  80. Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learning
  81. Automated transport separation using the neural shifted proper orthogonal decomposition
  82. A process algebraic framework for multi-agent dynamic epistemic systems
  83. SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devices
  84. Generative artificial intelligence in dentistry: Current approaches and future challenges
  85. I Could've Asked That: Reformulating Unanswerable Questions
  86. WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries
  87. CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models
  88. u-μP: The Unit-Scaled Maximal Update Parametrization
  89. Hidden or Inferred: Fair Learning-To-Rank with Unknown Demographics
  90. EuroCropsML: A Time Series Benchmark Dataset For Few-Shot Crop Type Classification
  91. CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition
  92. Automated Explanation Selection for Scientific Discovery
  93. Looking at Model Debiasing through the Lens of Anomaly Detection
  94. Fractional signature: a generalisation of the signature inspired by fractional calculus
  95. AHMF: Adaptive Hybrid-Memory-Fusion Model for Driver Attention Prediction
  96. HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
  97. Nerva: a Truly Sparse Implementation of Neural Networks
  98. 3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities
  99. A^* for Graphs of Convex Sets
  100. (PASS) Visual Prompt Locates Good Structure Sparsity through a Recurrent HyperNetwork
All 229
  1. Generation of Training Data from HD Maps in the Lanelet2 Framework
  2. Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models
  3. Grammar-based Game Description Generation using Large Language Models
  4. Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising
  5. 3D Question Answering for City Scene Understanding
  6. Systematic Relational Reasoning With Epistemic Graph Neural Networks
  7. The Costs of Pretending That There Are Data-Generating Probability Distributions in the Social World
  8. T5Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets
  9. Formalising causal inference as prediction on a target population
  10. A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance
  11. 2D and 3D Deep Learning Models for MRI-based Parkinson's Disease Classification: A Comparative Analysis of Convolutional Kolmogorov-Arnold Networks, Convolutional Neural Networks, and Graph Convolutional Networks
  12. PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Construction
  13. Entropy Reweighted Conformal Classification
  14. Co-designing an AI Impact Assessment Report Template with AI Practitioners and AI Compliance Experts
  15. ViPer: Visual Personalization of Generative Models via Individual Preference Learning
  16. MuST: Multi-Scale Transformers for Surgical Phase Recognition
  17. Quantile Learn-Then-Test: Quantile-Based Risk Control for Hyperparameter Optimization
  18. Gradient-based inference of abstract task representations for generalization in neural networks
  19. Deep Spherical Superpixels
  20. Scalify: scale propagation for efficient low-precision LLM training
  21. Label Alignment and Reassignment with Generalist Large Language Model for Enhanced Cross-Domain Named Entity Recognition
  22. Mathematical Programming Algorithms for Convex Hull Approximation with a Hyperplane Budget
  23. Preliminary study on artificial intelligence methods for cybersecurity threat detection in computer networks based on raw data packets
  24. Cascaded Light Propagation Volumes using Spherical Radial Basis Functions
  25. Global Confidence Degree Based Graph Neural Network for Financial Fraud Detection
  26. Multi-label Cluster Discrimination for Visual Representation Learning
  27. Low dimensional representation of multi-patient flow cytometry datasets using optimal transport for minimal residual disease detection in leukemia
  28. DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture
  29. Introducing DEFORMISE: A deep learning framework for dementia diagnosis in the elderly using optimized MRI slice selection
  30. Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patches
  31. LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering
  32. Enhanced SMC2: Leveraging Gradient Information from Differentiable Particle Filters Within Langevin Proposals
  33. A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks
  34. Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods
  35. Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation
  36. DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy
  37. SCIsegV2: A Universal Tool for Segmentation of Intramedullary Lesions in Spinal Cord Injury
  38. Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
  39. Channel-Aware Low-Rank Adaptation in Time Series Forecasting
  40. Statistical Batch-Based Bearing Fault Detection
  41. Improving ICD coding using Chapter based Named Entities and Attentional Models
  42. Artistic Intelligence: A Diffusion-Based Framework for High-Fidelity Landscape Painting Synthesis
  43. A Hybrid Federated Kernel Regularized Least Squares Algorithm
  44. Graph Neural Networks: A suitable Alternative to MLPs in Latent 3D Medical Image Classification?
  45. Alternating Iteratively Reweighted ℓ1 and Subspace Newton Algorithms for Nonconvex Sparse Optimization
  46. Application of Machine Learning and Convex Limiting to Subgrid Flux Modeling in the Shallow-Water Equations
  47. Spectrum-Informed Multistage Neural Networks: Multiscale Function Approximators of Machine Precision
  48. Nonverbal Immediacy Analysis in Education: A Multimodal Computational Model
  49. Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimization
  50. Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
  51. ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
  52. Surrogate-guided optimization in quantum networks
  53. A DeepONet for inverting the Neumann-to-Dirichlet Operator in Electrical Impedance Tomography: An approximation theoretic perspective and numerical results
  54. Trans2Unet: Neural fusion for Nuclei Semantic Segmentation
  55. NarrationDep: Narratives on Social Media For Automatic Depression Detection
  56. Speech Editing -- a Summary
  57. Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer
  58. Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model
  59. Explainable Artificial Intelligence Techniques for Irregular Temporal Classification of Multidrug Resistance Acquisition in Intensive Care Unit Patients
  60. Robust Deep Hawkes Process under Label Noise of Both Event and Occurrence
  61. dlordinal: a Python package for deep ordinal classification
  62. Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction
  63. Quantum Supervised Learning
  64. A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives
  65. Establishing Causal Relationship Between Whole Slide Image Predictions and Diagnostic Evidence Subregions in Deep Learning
  66. FIIH: Fully Invertible Image Hiding for Secure and Robust
  67. XMeCap: Meme Caption Generation with Sub-Image Adaptability
  68. SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle
  69. RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer
  70. SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)
  71. Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
  72. EverAdapt: Continuous Adaptation for Dynamic Machine Fault Diagnosis Environments
  73. A Self-Supervised Image Registration Approach for Measuring Local Response Patterns in Metastatic Ovarian Cancer
  74. PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning
  75. Towards Robust Knowledge Tracing Models via k-Sparse Attention
  76. Assessing Non-Nested Configurations of Multifidelity Machine Learning for Quantum-Chemical Properties
  77. OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos
  78. When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
  79. A Survey Forest Diagram : Gain a Divergent Insight View on a Specific Research Topic
  80. SAFETY-J: Evaluating Safety with Critique
  81. Contrastive Learning Is Not Optimal for Quasiperiodic Time Series
  82. An Efficient Procedure for Computing Bayesian Network Structure Learning
  83. Curriculum Negative Mining For Temporal Networks
  84. PatchFinder: A Two-Phase Approach to Security Patch Tracing for Disclosed Vulnerabilities in Open-Source Software
  85. AI-based Density Recognition
  86. DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting
  87. Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++
  88. Time Series Imputation with Multivariate Radial Basis Function Neural Network
  89. Q-Ground: Image Quality Grounding with Large Multi-modality Models
  90. Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance
  91. Enhancing Environmental Monitoring through Multispectral Imaging: The WasteMS Dataset for Semantic Segmentation of Lakeside Waste
  92. DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
  93. Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education
  94. EAFormer: Scene Text Segmentation with Edge-Aware Transformers
  95. Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism
  96. Pensieve Discuss: Scalable Small-Group CS Tutoring System with AI
  97. Progressive Query Refinement Framework for Bird's-Eye-View Semantic Segmentation from Surrounding Images
  98. SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing
  99. A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs
  100. LoFormer: Local Frequency Transformer for Image Deblurring
  101. DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction
  102. Orientation-Aware Sparse Tensor PCA for Efficient Unsupervised Feature Selection
  103. scGHSOM: Hierarchical clustering and visualization of single-cell and CRISPR data using growing hierarchical SOM
  104. Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
  105. On the Parameter Identifiability of Partially Observed Linear Causal Models
  106. Stochastic Variance-Reduced Iterative Hard Thresholding in Graph Sparsity Optimization
  107. When AI Defeats Password Deception! A Deep Learning Framework to Distinguish Passwords and Honeywords
  108. Toward an Integrated Decision Making Framework for Optimized Stroke Diagnosis with DSA and Treatment under Uncertainty
  109. Pose Estimation from Camera Images for Underwater Inspection
  110. Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding
  111. Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks
  112. Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal
  113. DVPE: Divided View Position Embedding for Multi-View 3D Object Detection
  114. Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applications
  115. Affective Behaviour Analysis via Progressive Learning
  116. Adaptive Gradient Regularization: A Faster and Generalizable Optimization Technique for Deep Neural Networks
  117. McGAN: Generating Manufacturable Designs by Embedding Manufacturing Rules into Conditional Generative Adversarial Network
  118. GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
  119. Early screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model
  120. Synthetic Trajectory Generation Through Convolutional Neural Networks
  121. Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
  122. Federated Automatic Latent Variable Selection in Multi-output Gaussian Processes
  123. Deep Koopman-based Control of Quality Variation in Multistage Manufacturing Systems
  124. Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance
  125. DeepCell: A Ubiquitous Accurate Provider-side Cellular-based Localization
  126. Handling Device Heterogeneity for Deep Learning-based Localization
  127. Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
  128. TelescopeML -- I. An End-to-End Python Package for Interpreting Telescope Datasets through Training Machine Learning Models, Generating Statistical Reports, and Visualizing Results
  129. Why Machines Can't Be Moral: Turing's Halting Problem and the Moral Limits of Artificial Intelligence