mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 9 Apr 2024

255 papers

  1. Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence AnalysisDeep reinforcement learning methods → RL for energy, networks and operations
  2. MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  3. Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' LabyrinthDeep reinforcement learning methods → RL for robot navigation and UAV control
  4. InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HDMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. MoReVQA: Exploring Modular Reasoning Models for Video Question AnsweringLLM reasoning → Multimodal reasoning
  6. Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying PerspectiveDeep reinforcement learning methods → RL for games and combinatorial optimization
  8. Visually Descriptive Language Model for Vector Graphics ReasoningLLM reasoning → Multimodal reasoning +1
  9. PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant CircuitsMechanistic interpretability → Circuits and mechanistic analysis
  10. Magic-Boost: Boost 3D Generation with Multi-View Conditioned DiffusionDiffusion models → 3D, point cloud and scene generation
  11. Deep Reinforcement Learning-Based Approach for a Single Vehicle Persistent Surveillance Problem with Fuel ConstraintsDeep reinforcement learning methods → RL for robot navigation and UAV control
  12. AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  13. Rethinking How to Evaluate Language Model JailbreakLLM reasoning → Reasoning for agents, planning and code +1
  14. Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO GeometryLLM reasoning → Spatial and embodied reasoning
  15. Latent Distance Guided Alignment Training for Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  16. Policy-Guided DiffusionWorld models → Latent dynamics models and model-based RL +1
  17. High Noise Scheduling is a MustDiffusion models → Diffusion foundations and sampling
  18. RAR-b: Reasoning as Retrieval BenchmarkLLM reasoning → Knowledge- and tool-augmented reasoning
  19. AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong LearningEnd-to-end autonomous driving → Large language models for driving
  20. Quantum State Generation with Structure-Preserving Diffusion ModelDiffusion models → Diffusion foundations and sampling
  21. Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  22. Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  23. Robust feature knowledge distillation for enhanced performance of lightweight crack segmentation modelsKnowledge distillation → Detection and dense prediction distillation
  24. Anchor-based Robust Finetuning of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  25. Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  26. CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as TeachersKnowledge distillation → Multimodal distillation
  27. scRDiT: Generating single-cell RNA-seq data by diffusion transformers and accelerating samplingDiffusion models → Flow matching, time series and science
  28. DiffHarmony: Latent Diffusion Model Meets Image HarmonizationDiffusion models → Image generation, text-to-image and editing
  29. Hash3D: Training-free Acceleration for 3D GenerationDiffusion models → 3D, point cloud and scene generation
  30. A RAG Method for Source Code Inquiry Tailored to Long-Context LLMsRetrieval-augmented generation → RAG for code
  31. Improving Facial Landmark Detection Accuracy and Efficiency with Knowledge DistillationKnowledge distillation → General knowledge distillation methods
  32. Prelimit Coupling and Steady-State Convergence of Constant-stepsize Nonsmooth Contractive SADeep reinforcement learning methods → RL theory and sample complexity
  33. Event-enhanced Retrieval in Real-time SearchRetrieval-augmented generation → Generation and context integration
  34. Tackling Structural Hallucination in Image Translation with Local DiffusionDiffusion models → Medical imaging and segmentation
  35. Does Transformer Interpretability Transfer to RNNs?State-space sequence models (S4, Mamba) → Core SSM architectures for language
  36. Optimization Methods for Personalizing Large Language Models through Retrieval AugmentationRetrieval-augmented generation → RAG pipeline design and evaluation
  37. THOUGHTSCULPT: Reasoning with Intermediate Revision and SearchLLM reasoning → Test-time compute and efficient thinking
  38. VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
  39. Efficient Multi-Task Reinforcement Learning via Task-Specific Action CorrectionDeep reinforcement learning methods → Deep RL algorithms and representations
  40. Kermut: Composite kernel regression for protein variant effects
  41. Traitement quantique des langues : 'etat de l'art
  42. End-to-End Rate-Distortion Optimized 3D Gaussian Representation
  43. Exploring the limitations of blood pressure estimation using the photoplethysmography signal
  44. GUIDE: Graphical User Interface Data for Execution
  45. Integrative Deep Learning Framework for Parkinson's Disease Early Detection using Gait Cycle Data Measured by Wearable Sensors: A CNN-GRU-GNN Approach
  46. Text2Grasp: Grasp synthesis by text prompts of object grasping parts
  47. "Hey..! This medicine made me sick": Sentiment Analysis of User-Generated Drug Reviews using Machine Learning Techniques
  48. Graph Vertex Embeddings: Distance, Regularization and Community Detection
  49. Towards Building a Robust Toxicity Predictor
  50. A Survey of Reasoning for Substitution Relationships: Definitions, Methods, and Directions
  51. Extractive text summarisation of Privacy Policy documents using machine learning approaches
  52. Interpretable Neural Temporal Point Processes for Modelling Electronic Health Records
  53. Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking
  54. Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAS
  55. GRANP: A Graph Recurrent Attentive Neural Process Model for Vehicle Trajectory Prediction
  56. Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
  57. Radiomics and artificial Intelligence for thyroid cancer diagnosis: Concepts, challenges, and solutions
  58. Leveraging Interesting Facts to Enhance User Engagement with Conversational Interfaces
  59. Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction
  60. RULER: What's the Real Context Size of Your Long-Context Language Models?
  61. FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
  62. From Protoscience to Epistemic Monoculture: How Benchmarking Set the Stage for the Deep Learning Revolution
  63. GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Tasks
  64. Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?
  65. Federated learning model for predicting major postoperative complications
  66. SAM-I-Am: Semantic Boosting for Zero-shot Atomic-Scale Electron Micrograph Segmentation
  67. GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis
  68. Evolving Loss Functions for Specific Image Augmentation Techniques
  69. Counting Objects in a Robotic Hand
  70. Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
  71. What is Your Favorite Gender, MLM? Gender Bias Evaluation in Multilingual Masked Language Models
  72. FairPair: A Robust Evaluation of Biases in Language Models through Paired Perturbations
  73. GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation
  74. RoadBEV: Road Surface Reconstruction in Bird's Eye View
  75. Collaborative Multi-source Domain Adaptation Through Optimal Transport
  76. Spatially Optimized Compact Deep Metric Learning Model for Similarity Search
  77. Leveraging Latents for Efficient Thermography Classification and Segmentation
  78. Lecture notes on rough paths and applications to machine learning
  79. Less is More for Improving Automatic Evaluation of Factual Consistency
  80. Building A Knowledge Graph to Enrich ChatGPT Responses in Manufacturing Service Discovery
  81. Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows
  82. Learning Strategies For Successful Crowd Navigation
  83. The Impact of Print-Scanning in Heterogeneous Morph Evaluation Scenarios
  84. Variational Stochastic Gradient Descent for Deep Neural Networks
  85. Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation
  86. Learning to rank quantum circuits for hardware-optimized performance enhancement
  87. An Enhanced Grey Wolf Optimizer with Elite Inheritance and Balance Search Mechanisms
  88. On the Effect of (Near) Duplicate Subwords in Language Modelling
  89. Reconstructing Hand-Held Objects in 3D from Images and Videos
  90. Comparing Two Model Designs for Clinical Note Generation; Is an LLM a Useful Evaluator of Consistency?
  91. Simultaneous linear connectivity of neural networks modulo permutation
  92. Flying with Photons: Rendering Novel Views of Propagating Light
  93. Pitfalls of Conversational LLMs on News Debiasing
  94. GO4Align: Group Optimization for Multi-Task Alignment
  95. Public-private funding models in open source software development: A case study on scikit-learn
  96. RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement
  97. GeoDirDock: Guiding Docking Along Geodesic Paths
  98. Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks
  99. Autonomous Evaluation and Refinement of Digital Agents
  100. A Dataset and Framework for Learning State-invariant Object Representations
All 255
  1. Hyperparameter Selection in Continual Learning
  2. Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Prediction
  3. A comparative analysis of deep learning models for lung segmentation on X-ray images
  4. SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions
  5. Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models
  6. The Central Spanning Tree Problem
  7. Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition
  8. QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding
  9. Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks
  10. pfl-research: simulation framework for accelerating research in Private Federated Learning
  11. ZeST: Zero-Shot Material Transfer from a Single Image
  12. Efficient Training of Probabilistic Neural Networks for Survival Analysis
  13. Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstruction
  14. Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems
  15. Emergent Dynamics in Neural Cellular Automata
  16. Apprentices to Research Assistants: Advancing Research with Large Language Models
  17. Online Learning of Decision Trees with Thompson Sampling
  18. Dynamic Deep Learning Based Super-Resolution For The Shallow Water Equations
  19. MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
  20. MuPT: A Generative Symbolic Music Pretrained Transformer
  21. Event Extraction in Basque: Typologically motivated Cross-Lingual Transfer-Learning Analysis
  22. Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity
  23. Raster Forge: Interactive Raster Manipulation Library and GUI for Python
  24. Model Generation with LLMs: From Requirements to UML Sequence Diagrams
  25. Enhancing Decision Analysis with a Large Language Model: pyDecision a Comprehensive Library of MCDA Methods in Python
  26. WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs
  27. ClinLinker: Medical Entity Linking of Clinical Concept Mentions in Spanish
  28. Dynamic Resolution Guidance for Facial Expression Recognition
  29. SurveyAgent: A Conversational System for Personalized and Efficient Research Survey
  30. Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
  31. Generalizable Sarcasm Detection Is Just Around The Corner, Of Course!
  32. DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning
  33. HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention
  34. Rolling Shutter Correction with Intermediate Distortion Flow Estimation
  35. CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
  36. Finding fake reviews in e-commerce platforms by using hybrid algorithms
  37. Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences
  38. What is the textitintrinsic dimension of your binary data? -- and how to compute it quickly
  39. Automatically Learning HTN Methods from Landmarks
  40. Dynamic D2D-Assisted Federated Learning over O-RAN: Performance Analysis, MAC Scheduler, and Asymmetric User Selection
  41. Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
  42. On adversarial training and the 1 Nearest Neighbor classifier
  43. Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures
  44. nEMO: Dataset of Emotional Speech in Polish
  45. Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
  46. LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements
  47. Simple algorithms to test and learn local Hamiltonians
  48. Algorithms for Caching and MTS with reduced number of predictions
  49. NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata
  50. Dimensionality Reduction in Sentence Transformer Vector Databases with Fast Fourier Transform
  51. Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping
  52. Robust Confidence Intervals in Stereo Matching using Possibility Theory
  53. 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis
  54. PGTNet: A Process Graph Transformer Network for Remaining Time Prediction of Business Process Instances
  55. Spatial-Temporal Multi-level Association for Video Object Segmentation
  56. Playing to Vision Foundation Model's Strengths in Stereo Matching
  57. Label-Efficient 3D Object Detection For Road-Side Units
  58. From Barlow Twins to Triplet Training: Differentiating Dementia with Limited Data
  59. ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization
  60. LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
  61. GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields
  62. ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos
  63. Hyperparameter-Free Medical Image Synthesis for Sharing Data and Improving Site-Specific Segmentation
  64. Towards Robust Domain Generation Algorithm Classification
  65. Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning
  66. Autonomous Driving Small-Scale Cars: A Survey of Recent Development
  67. Understanding Cross-Lingual Alignment -- A Survey
  68. Message Passing Variational Autoregressive Network for Solving Intractable Ising Models
  69. Low-Cost Generation and Evaluation of Dictionary Example Sentences
  70. Zero-Shot Relational Learning for Multimodal Knowledge Graphs
  71. Automatic Defect Detection in Sewer Network Using Deep Learning Based Object Detector
  72. Quantum Circuit C^*-algebra Net
  73. VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection
  74. [Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
  75. OmniFusion Technical Report
  76. Unified Physical-Digital Attack Detection Challenge
  77. Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models
  78. Leveraging edge detection and neural networks for better UAV localization
  79. Deep Learning Method for Computing Committor Functions with Adaptive Sampling
  80. Automated National Urban Map Extraction
  81. Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning
  82. Further Understanding of a Local Gaussian Process Approximation: Characterising Convergence in the Finite Regime
  83. The impact of data set similarity and diversity on transfer learning success in time series forecasting
  84. Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection
  85. Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles
  86. EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation
  87. YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images
  88. Uncertainty-aware Evidential Fusion-based Learning for Semi-supervised Medical Image Segmentation
  89. Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank
  90. scCDCG: Efficient Deep Structural Clustering for single-cell RNA-seq via Deep Cut-informed Graph Embedding
  91. Enhanced Radar Perception via Multi-Task Learning: Towards Refined Data for Sensor Fusion Applications
  92. Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports
  93. Efficient and Robust Point Cloud Registration via Heuristics-guided Parameter Search
  94. Concise Plane Arrangements for Low-Poly Surface and Volume Modelling
  95. HFNeRF: Learning Human Biomechanic Features with Neural Radiance Fields
  96. (Not) Understanding Latin Poetic Style with Deep Learning
  97. Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability
  98. Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages
  99. SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection
  100. Efficient Concertormer for Image Deblurring and Beyond
  101. Adaptable Recovery Behaviors in Robotics: A Behavior Trees and Motion Generators(BTMG) Approach for Failure Management
  102. Gaussian Pancakes: Geometrically-Regularized 3D Gaussian Splatting for Realistic Endoscopic Reconstruction
  103. FLEX: FLEXible Federated Learning Framework
  104. Learning Model Predictive Control Parameters via Bayesian Optimization for Battery Fast Charging
  105. Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation
  106. Detection of fields of applications in biomedical abstracts with the support of argumentation elements
  107. DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation
  108. Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey
  109. Revising Densification in Gaussian Splatting
  110. Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets
  111. Unifying Low Dimensional Spectra in Deep Learning
  112. A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on n-dimensional Classes
  113. Making Old Kurdish Publications Processable by Augmenting Available Optical Character Recognition Engines
  114. Fair Graph Neural Network with Supervised Contrastive Regularization
  115. Using Few-Shot Learning to Classify Primary Lung Cancer and Other Malignancy with Lung Metastasis in Cytological Imaging via Endobronchial Ultrasound Procedures
  116. The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge
  117. Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineage
  118. LIPT: Latency-aware Image Processing Transformer
  119. Unified Entropy Optimization for Open-Set Test-Time Adaptation
  120. Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis
  121. Efficient Quantum Circuits for Machine Learning Activation Functions including Constant T-depth ReLU
  122. Unified Multi-modal Diagnostic Framework with Reconstruction Pre-training and Heterogeneity-combat Tuning
  123. Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes
  124. Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
  125. Space-Time Video Super-resolution with Neural Operator
  126. Little Strokes Fell Great Oaks: Boosting the Hierarchical Features for Multi-exposure Image Fusion
  127. Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs
  128. Band-Attention Modulation Network for Robust Face Forgery Detection
  129. Identifying Shopping Intent in Product QA for Proactive Recommendations
  130. Using 3-Objective Evolutionary Algorithms for the Dynamic Chance Constrained Knapsack Problem
  131. Feel-Good Thompson Sampling for Contextual Dueling Bandits
  132. Diffusion-Based Point Cloud Super-Resolution for mmWave Radar Data
  133. Collaborative Edge AI Inference over Cloud-RAN
  134. AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information Retrieval
  135. FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models
  136. Privacy Preserving Prompt Engineering: A Survey
  137. Concept-Attention Whitening for Interpretable Skin Lesion Diagnosis
  138. AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
  139. Polynomial-time derivation of optimal k-tree topology from Markov networks
  140. Automatic Authorities: Power and AI
  141. Boosting Digital Safeguards: Blending Cryptography and Steganography
  142. A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics
  143. StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion
  144. A Cyber Manufacturing IoT System for Adaptive Machine Learning Model Deployment by Interactive Causality Enabled Self-Labeling
  145. JSTR: Judgment Improves Scene Text Recognition
  146. LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
  147. EasyTrack: Efficient and Compact One-stream 3D Point Clouds Tracker
  148. Map Optical Properties to Subwavelength Structures Directly via a Diffusion Model
  149. Interplay of Machine Translation, Diacritics, and Diacritization
  150. Neural networks can be FLOP-efficient integrators of 1D oscillatory integrands
  151. Inclusive Practices for Child-Centered AI Design and Testing
  152. AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression
  153. Prompt-driven Universal Model for View-Agnostic Echocardiography Analysis
  154. Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus
  155. LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation