mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 24 Jan 2024

206 papers

  1. Large language model empowered participatory urban planningLLM agents and tool use → Social simulation and multi-agent debate
  2. Language-Guided World Models: A Model-Based Approach to AI ControlWorld models → World models for language agents
  3. M3TN: Multi-gate Mixture-of-Experts based Multi-valued Treatment Network for Uplift ModelingMixture-of-experts → MoE large language models
  4. No Longer Trending on Artstation: Prompt Analysis of Generative AI ArtDiffusion models → Image generation, text-to-image and editing
  5. Graph Diffusion Transformers for Multi-Conditional Molecular GenerationDiffusion models → Flow matching, time series and science
  6. Embedding Attack Project (Work Report)LLM safety and security → Membership inference attacks
  7. TPD: Enhancing Student Language Model Reasoning via Principle Discovery and GuidanceLLM reasoning → Prompting and chain-of-thought reasoning
  8. What Large Language Models Know and What People Think They KnowLLM reasoning → Reasoning benchmarks and evaluation
  9. Diffuse to Choose: Enriching Image Conditioned Inpainting in Latent Diffusion Models for Virtual Try-AllDiffusion models → 3D, point cloud and scene generation
  10. Inference Attacks Against Face Recognition Model without Classification LayersLLM safety and security → Membership inference attacks
  11. The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and ImplementationsDeep reinforcement learning methods → RL theory and sample complexity
  12. MambaByte: Token-free Selective State Space ModelState-space sequence models (S4, Mamba) → Core SSM architectures for language +1
  13. VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web TasksLLM agents and tool use → Web, search, and research agents
  14. MM-LLMs: Recent Advances in MultiModal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  15. Guided Diffusion for Fast Inverse Design of Density-based Mechanical MetamaterialsDiffusion models → Flow matching, time series and science
  16. SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  17. SpeechGPT-Gen: Scaling Chain-of-Information Speech GenerationDiffusion models → Audio, speech and music
  18. Symbolic Equation Solving via Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  19. How to Forget Clients in Federated Online Learning to Rank?LLM safety and security → Federated unlearning and poisoning
  20. UNIMO-G: Unified Image Generation through Multimodal Conditional DiffusionDiffusion models → Image generation, text-to-image and editing
  21. TraKDis: A Transformer-based Knowledge Distillation Approach for Visual Reinforcement Learning with Application to Cloth ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  22. Generative Video Diffusion for Unseen Novel Semantic Video Moment RetrievalDiffusion models → Video generation
  23. ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal ModelsLLM reasoning → Multimodal reasoning +1
  24. UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue SystemsRetrieval-augmented generation → Conversational and speech RAG
  25. SEER: Facilitating Structured Reasoning and Explanation via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
  26. TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual DataLLM reasoning → Knowledge- and tool-augmented reasoning
  27. It's About Time: Incorporating Temporality in Retrieval Augmented Language ModelsRetrieval-augmented generation → Generation and context integration
  28. MLLMReID: Multimodal Large Language Model-based Person Re-identificationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  29. Generative Design of Crystal Structures by Point Cloud Representations and Diffusion ModelDiffusion models → Flow matching, time series and science
  30. Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion modelDiffusion models → Image generation, text-to-image and editing
  31. AgentBoard: An Analytical Evaluation Board of Multi-turn LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. Towards Customized Knowledge Distillation for Chip-Level Dense Image PredictionsKnowledge distillation → Detection and dense prediction distillation
  33. Compositional Generative Inverse DesignDiffusion models → Flow matching, time series and science
  34. Predicting SSH keys in Open SSH Memory dumps
  35. Machine Learning in Proton Exchange Membrane Water Electrolysis -- Part I: A Knowledge-Integrated Framework
  36. Bike3S: A Tool for Bike Sharing Systems Simulation
  37. An Enhanced Analysis of Traffic Intelligence in Smart Cities Using Sustainable Deep Radial Function
  38. WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing
  39. DoorINet: Door Heading Prediction through Inertial Deep Learning
  40. Is 3-(F)WL Enough to Distinguish All 3D Graphs?
  41. Causal Relationship Network of Risk Factors Impacting Workday Loss in Underground Coal Mines
  42. Analysis of Hopfield Model as Associative Memory
  43. Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications
  44. Steering Language Models with Game-Theoretic Solvers
  45. Community-Informed AI Models for Police Accountability
  46. Fluent dreaming for language models
  47. Question answering systems for health professionals at the point of care -- a systematic review
  48. APT-Pipe: A Prompt-Tuning Tool for Social Data Annotation using ChatGPT
  49. HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification
  50. Compiling High-Level Neural Network Specifications into VNN-LIB Queries
  51. IICONGRAPH: improved Iconographic and Iconological Statements in Knowledge Graphs
  52. Better Call GPT, Comparing Large Language Models Against Lawyers
  53. [Re] The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Non-Gaussian Observation Models
  54. Beimingwu: A Learnware Dock System
  55. Discovering Mathematical Formulas from Data via GPT-guided Monte Carlo Tree Search
  56. Prompt Design and Engineering: Introduction and Advanced Methods
  57. Location Agnostic Source-Free Domain Adaptive Learning to Predict Solar Power Generation
  58. Speech foundation models on intelligibility prediction for hearing-impaired listeners
  59. LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection
  60. Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perception
  61. Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages
  62. A V2X-based Privacy Preserving Federated Measuring and Learning System
  63. Enumerating the k-fold configurations in multi-class classification problems
  64. Democratizing Fine-grained Visual Recognition with Large Language Models
  65. Machine learning for industrial sensing and control: A survey and practical perspective
  66. Traffic Learning and Proactive UAV Trajectory Planning for Data Uplink in Markovian IoT Models
  67. Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on Hugging Face
  68. Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4
  69. Investigating the Efficacy of Large Language Models for Code Clone Detection
  70. Multi-Object Navigation in real environments using hybrid policies
  71. Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning
  72. Traffic Pattern Classification in Smart Cities Using Deep Recurrent Neural Network
  73. A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling
  74. FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization
  75. A Spatiotemporal Approach to Tri-Perspective Representation for 3D Semantic Occupancy Prediction
  76. Position: AI/ML Influencers Have a Place in the Academic Process
  77. Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks
  78. AlphaMapleSAT: An MCTS-based Cube-and-Conquer SAT Solver for Hard Combinatorial Problems
  79. Multiview Graph Learning with Consensus Graph
  80. Assumptions and Bounds in the Instrumental Variable Model
  81. NLICE: Synthetic Medical Record Generation for Effective Primary Healthcare Differential Diagnosis
  82. Explaining Image Classifiers
  83. A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)
  84. Conformal Prediction Sets Improve Human Decision Making
  85. Supporting Sensemaking of Large Language Model Outputs at Scale
  86. Proactive Emotion Tracker: AI-Driven Continuous Mood and Emotion Monitoring
  87. Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression
  88. Can I trust my fake data -- A comprehensive quality assessment framework for synthetic tabular data in healthcare
  89. Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
  90. EMP: Effective Multidimensional Persistence for Graph Representation Learning
  91. Algebraic methods for solving recognition problems with non-crossing classes
  92. Entrywise Inference for Missing Panel Data: A Simple and Instance-Optimal Approach
  93. Inadequacy of common stochastic neural networks for reliable clinical decision support
  94. Graph-Instructed Neural Networks for Sparse Grid-Based Discontinuity Detectors
  95. Tyche: Stochastic In-Context Learning for Medical Image Segmentation
  96. How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability
  97. Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
  98. Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint
  99. DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning
  100. FLLIC: Functionally Lossless Image Compression
All 206
  1. Enhancing Image Retrieval : A Comprehensive Study on Photo Search using the CLIP Mode
  2. Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models
  3. Stream-based perception for cognitive agents in mobile ecosystems
  4. Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction
  5. PLATE: A perception-latency aware estimator,
  6. Graph Guided Question Answer Generation for Procedural Question-Answering
  7. Evaluation of General Large Language Models in Contextually Assessing Semantic Concepts Extracted from Adult Critical Care Electronic Health Record Notes
  8. Instruction Fine-Tuning: Does Prompt Loss Matter?
  9. Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregation
  10. CNN architecture extraction on edge GPU
  11. Large Malaysian Language Model Based on Mistral for Enhanced Local Language Understanding
  12. Task structure and nonlinearity jointly determine learned representational geometry
  13. Benchmarking the Fairness of Image Upsampling Methods
  14. PanAf20K: A Large Video Dataset for Wild Ape Detection and Behaviour Recognition
  15. Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection
  16. Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
  17. Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
  18. Finetuning Foundation Models for Joint Analysis Optimization
  19. QAGait: Revisit Gait Recognition from a Quality Perspective
  20. Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
  21. Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces
  22. Can GPT-3.5 Generate and Code Discharge Summaries?
  23. Tissue Cross-Section and Pen Marking Segmentation in Whole Slide Images
  24. Generative Human Motion Stylization in Latent Space
  25. Research about the Ability of LLM in the Tamper-Detection Area
  26. Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interaction
  27. LDCA: Local Descriptors with Contextual Augmentation for Few-Shot Learning
  28. Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting
  29. Separable Physics-Informed Neural Networks for the solution of elasticity problems
  30. How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment
  31. SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
  32. Segmenting Cardiac Muscle Z-disks with Deep Neural Networks
  33. SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering
  34. Growing from Exploration: A self-exploring framework for robots based on foundation models
  35. Multi-Agent Diagnostics for Robustness via Illuminated Diversity
  36. Fine-grained Stateful Knowledge Exploration: Effective and Efficient Graph Retrieval with Large Language Models
  37. Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond
  38. Detection of Correlated Random Vectors
  39. Federated learning with distributed fixed design quantum chips and quantum channels
  40. Serial fusion of multi-modal biometric systems
  41. GTAutoAct: An Automatic Datasets Generation Framework Based on Game Engine Redevelopment for Action Recognition
  42. Toward A Causal Framework for Modeling Perception
  43. Synthetic data enables faster annotation and robust segmentation for multi-object grasping in clutter
  44. SEDNet: Shallow Encoder-Decoder Network for Brain Tumor Segmentation
  45. Text Categorization Can Enhance Domain-Agnostic Stopword Extraction
  46. Reranking individuals: The effect of fair classification within-groups
  47. Privacy-Preserving Face Recognition in Hybrid Frequency-Color Domain
  48. Mitigating System Bias in Resource Constrained Asynchronous Federated Learning Systems
  49. Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons
  50. Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
  51. Linear Relative Pose Estimation Founded on Pose-only Imaging Geometry
  52. EndoGaussians: Single View Dynamic Gaussian Splatting for Deformable Endoscopic Tissues Reconstruction
  53. Past, Present, Future: A Comprehensive Exploration of AI Use Cases in the UMBRELLA IoT Testbed
  54. Lessons on Datasets and Paradigms in Machine Learning for Symbolic Computation: A Case Study on CAD
  55. Full Bayesian Significance Testing for Neural Networks
  56. Explainable Bayesian Optimization
  57. NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
  58. Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
  59. Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery
  60. Information That Matters: Exploring Information Needs of People Affected by Algorithmic Decisions
  61. Deep Learning for Improved Polyp Detection from Synthetic Narrow-Band Imaging
  62. An Explicit Scheme for Pathwise XVA Computations
  63. InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions
  64. ChatterBox: Multi-round Multimodal Referring and Grounding
  65. MaLA-500: Massive Language Adaptation of Large Language Models
  66. Classification of Radiologically Isolated Syndrome and Clinically Isolated Syndrome with Machine-Learning Techniques
  67. Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
  68. Visual Objectification in Films: Towards a New AI Task for Video Interpretation
  69. Small Object Tracking in LiDAR Point Cloud: Learning the Target-awareness Prototype and Fine-grained Search Region
  70. RefreshNet: Learning Multiscale Dynamics through Hierarchical Refreshing
  71. DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection
  72. Can AI Assistants Know What They Don't Know?
  73. Audio-Infused Automatic Image Colorization by Exploiting Audio Scene Semantics
  74. Dynamic Traceback Learning for Medical Report Generation
  75. Enhancing cross-domain detection: adaptive class-aware contrastive transformer
  76. Designing Redistribution Mechanisms for Reducing Transaction Fees in Blockchains
  77. MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction
  78. Adaptive Crowdsourcing Via Self-Supervised Learning
  79. Quantum natural gradient without monotonicity
  80. How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learning
  81. DittoGym: Learning to Control Soft Shape-Shifting Robots
  82. From Random to Informed Data Selection: A Diversity-Based Approach to Optimize Human Annotation and Few-Shot Learning
  83. LPNL: Scalable Link Prediction with Large Language Models
  84. Unified-Width Adaptive Dynamic Network for All-In-One Image Restoration
  85. Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation
  86. TEPI: Taxonomy-aware Embedding and Pseudo-Imaging for Scarcely-labeled Zero-shot Genome Classification
  87. ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement
  88. On Principled Local Optimization Methods for Federated Learning
  89. AMANet: Advancing SAR Ship Detection with Adaptive Multi-Hierarchical Attention Network
  90. Common-Sense Bias Modeling for Classification Tasks
  91. AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation
  92. Multitask Active Learning for Graph Anomaly Detection
  93. Self-Improving Interference Management Based on Deep Learning With Uncertainty Quantification
  94. Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size
  95. Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects
  96. Topology-aware Embedding Memory for Continual Learning on Expanding Networks
  97. Predicting Mitral Valve mTEER Surgery Outcomes Using Machine Learning and Deep Learning Techniques
  98. Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
  99. Fast Partition-Based Cross-Validation With Centering and Scaling for XTX and XTY
  100. Deep Learning Model Reuse in the HuggingFace Community: Challenges, Benefit and Trends
  101. ADMap: Anti-disturbance framework for reconstructing online vectorized HD map
  102. CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert Judgments For Open-Domain Question Answering
  103. Misgendering and Assuming Gender in Machine Translation when Working with Low-Resource Languages
  104. A Generalized Multiscale Bundle-Based Hyperspectral Sparse Unmixing Algorithm
  105. SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection
  106. Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence