mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 21 Sep 2024

135 papers

  1. LLM Agents as 6G Orchestrator: A Paradigm for Task-Oriented Physical-Layer AutomationLLM agents and tool use → Agentic AI for wireless networks
  2. StateAct: Enhancing LLM Base Agents via Self-prompting and State-trackingLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. Towards Automated Patent Workflows: AI-Orchestrated Multi-Agent Framework for Intellectual Property Management and AnalysisLLM agents and tool use → Web, search, and research agents
  4. A Survey on Multimodal Benchmarks: In the Era of Large AI ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  5. Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image GenerationLLM safety and security → Vision-language and text-to-image safety
  6. Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  7. Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving ProcessLLM agents and tool use → Educational agents and math problem solving
  8. R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World ModelsWorld models → World models for language agents +1
  9. @Bench: Benchmarking Vision-Language Models for Human-centered Assistive TechnologyMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Data-centric NLP Backdoor Defense from the Lens of MemorizationLLM safety and security → Backdoor and data poisoning attacks
  11. Adversarial and Reactive Traffic Entities for Behavior-Realistic Driving Simulation: A ReviewEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  12. PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak ApproachLLM safety and security → Jailbreaking
  13. QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option ShufflingRetrieval-augmented generation → RAG robustness and adaptive retrieval
  14. A Survey on Large Language Model-empowered Autonomous DrivingEnd-to-end autonomous driving → Large language models for driving
  15. JVID: Joint Video-Image Diffusion for Visual-Quality and Temporal-Consistency in Video GenerationDiffusion models → Video generation
  16. Vision-Language Models Assisted Unsupervised Video Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  17. Routing in Sparsely-gated Language Models responds to ContextMixture-of-experts → Expert routing strategies
  18. Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer PredictionEfficient LLM inference and serving → Early exit and edge inference
  19. One-shot World Models Using a Transformer Trained on a Synthetic PriorWorld models → Latent predictive world models
  20. SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved InformationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  21. PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
  22. KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot DataMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  23. GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group DiscussionLLM reasoning → Reasoning for agents, planning and code +1
  24. Maximum-Likelihood Estimation Based on Diffusion Model For Wireless CommunicationsDiffusion models → Diffusion for compression and wireless
  25. Uncovering Latent Chain of Thought Vectors in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  26. Mitigating Exposure Bias in Score-Based Generation of Molecular ConformationsDiffusion models → Flow matching, time series and science
  27. Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision TransformerEfficient LLM inference and serving → Early exit and edge inference
  28. Integrated Decision Making and Trajectory Planning for Autonomous Driving Under Multimodal Uncertainties: A Bayesian Game ApproachEnd-to-end autonomous driving → Cooperative and V2X driving
  29. SMART-RAG: Selection using Determinantal Matrices for Augmented RetrievalRetrieval-augmented generation → RAG pipeline design and evaluation
  30. Enhancing Advanced Visual Reasoning Ability of Large Language ModelsLLM reasoning → Multimodal reasoning +1
  31. Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical DilemmasLLM reasoning → Reasoning benchmarks and evaluation +1
  32. The trade-off between data minimization and fairness in collaborative filtering
  33. Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks
  34. What is a Digital Twin Anyway? Deriving the Definition for the Built Environment from over 15,000 Scientific Publications
  35. WeatherFormer: Empowering Global Numerical Weather Forecasting with Space-Time Transformer
  36. Developing a Thailand solar irradiance map using Himawari-8 satellite imageries and deep learning models
  37. BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow
  38. Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics
  39. Combining Absolute and Semi-Generalized Relative Poses for Visual Localization
  40. FeDETR: a Federated Approach for Stenosis Detection in Coronary Angiography
  41. Instruction Following without Instruction Tuning
  42. End to End Face Reconstruction via Differentiable PnP
  43. Cloud Adversarial Example Generation for Remote Sensing Image Classification
  44. An Instance-based Plus Ensemble Learning Method for Classification of Scientific Papers
  45. Structure Learning via Mutual Information
  46. ReFine: Boosting Time Series Prediction of Extreme Events by Reweighting and Fine-tuning
  47. Predicting Coronary Heart Disease Using a Suite of Machine Learning Models
  48. Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking
  49. MEGA-PT: A Meta-Game Framework for Agile Penetration Testing
  50. AI Assistants for Spaceflight Procedures: Combining Generative Pre-Trained Transformer and Retrieval-Augmented Generation on Knowledge Graphs With Augmented Reality Cues
  51. Egocentric zone-aware action recognition across environments
  52. A Unified Deep Learning Framework for Motion Correction in Medical Imaging
  53. Mining Causality: AI-Assisted Search for Instrumental Variables
  54. LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement
  55. Loop Neural Networks for Parameter Sharing
  56. A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer
  57. Advancing Employee Behavior Analysis through Synthetic Data: Leveraging ABMs, GANs, and Statistical Models for Enhanced Organizational Efficiency
  58. The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
  59. Data-Driven Approach to assess and identify gaps in healthcare set up in South Asia
  60. Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extraction
  61. Addressing and Visualizing Misalignments in Human Task-Solving Trajectories
  62. Content-aware Tile Generation using Exterior Boundary Inpainting
  63. Democratising Artificial Intelligence for Pandemic Preparedness and Global Governance in Latin American and Caribbean Countries
  64. On Lexical Invariance on Multisets and Graphs
  65. FlowRL: Flow-Augmented Few-Shot Reinforcement Learning for Semi-Structured Sensor Data
  66. Component-based Sketching for Deep ReLU Nets
  67. An Evolutionary Algorithm For the Vehicle Routing Problem with Drones with Interceptions
  68. LFP: Efficient and Accurate End-to-End Lane-Level Planning via Camera-LiDAR Fusion
  69. Towards Building Efficient Sentence BERT Models using Layer Pruning
  70. PromptTA: Prompt-driven Text Adapter for Source-free Domain Generalization
  71. On Importance of Pruning and Distillation for Efficient Low Resource NLP
  72. When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning
  73. Price predictability in limit order book with deep learning model
  74. MSSDA: Multi-Sub-Source Adaptation for Diabetic Foot Neuropathy Recognition
  75. Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
  76. A Feature Generator for Few-Shot Learning
  77. Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
  78. Present and Future Generalization of Synthetic Image Detectors
  79. Consistency for Large Neural Networks: Regression and Classification
  80. Efficient and Effective Model Extraction
  81. CONGRA: Benchmarking Automatic Conflict Resolution
  82. Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
  83. Accelerated Multi-Contrast MRI Reconstruction via Frequency and Spatial Mutual Learning
  84. Advancing Molecular Graph-Text Pre-training via Fine-grained Alignment
  85. ESDS: AI-Powered Early Stunting Detection and Monitoring System using Edited Radius-SMOTE Algorithm
  86. ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events
  87. PoseAugment: Generative Human Pose Data Augmentation with Physical Plausibility for IMU-based Motion Capture
  88. Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers
  89. Foundation Models for Amodal Video Instance Segmentation in Automated Driving
  90. Window-based Channel Attention for Wavelet-enhanced Learned Image Compression
  91. Quantum enhanced stratification of Breast Cancer: exploring quantum expressivity for real omics data
  92. BRep Boundary and Junction Detection for CAD Reverse Engineering
  93. AMT-APC: Automatic Piano Cover by Fine-Tuning an Automatic Music Transcription Model
  94. MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
  95. Dynamic 2D Gaussians: Geometrically Accurate Radiance Fields for Dynamic Objects
  96. N-Version Assessment and Enhancement of Generative AI
  97. SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality
  98. Temporally Consistent Factuality Probing for Large Language Models
  99. Recovering Global Data Distribution Locally in Federated Learning
  100. Soft Segmented Randomization: Enhancing Domain Generalization in SAR-ATR for Synthetic-to-Measured
All 135
  1. Co-occurrence is not Factual Association in Language Models
  2. The use of GPT-4o and Other Large Language Models for the Improvement and Design of Self-Assessment Scales for Measurement of Interpersonal Communication Skills
  3. ECHO: Environmental Sound Classification with Hierarchical Ontology-guided Semi-Supervised Learning
  4. PepINVENT: Generative peptide design beyond the natural amino acids
  5. OAEI-LLM: A Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching
  6. Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators
  7. Implicit Neural Representations for Speed-of-Sound Estimation in Ultrasound
  8. MSDet: Receptive Field Enhanced Multiscale Detection for Tiny Pulmonary Nodule
  9. FAMOUS: Flexible Accelerator for the Attention Mechanism of Transformer on UltraScale+ FPGAs
  10. BrainDreamer: Reasoning-Coherent and Controllable Image Generation from EEG Brain Signals via Language Guidance
  11. MOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors
  12. Enhancing Multivariate Time Series-based Solar Flare Prediction with Multifaceted Preprocessing and Contrastive Learning
  13. ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation
  14. Test Time Learning for Time Series Forecasting
  15. Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors
  16. Boolean Product Graph Neural Networks
  17. Graph Neural Network Framework for Sentiment Analysis Using Syntactic Feature
  18. Relevance-driven Decision Making for Safer and More Efficient Human Robot Collaboration
  19. Drift to Remember
  20. Contrastive Learning for Knowledge-Based Question Generation in Large Language Models
  21. ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
  22. GAInS: Gradient Anomaly-aware Biomedical Instance Segmentation
  23. Holistic and Historical Instance Comparison for Cervical Cell Detection
  24. Cycle-Consistency Uncertainty Estimation for Visual Prompting based One-Shot Defect Segmentation
  25. Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds
  26. CUS3D :CLIP-based Unsupervised 3D Segmentation via Object-level Denoise
  27. FracGM: A Fast Fractional Programming Technique for Geman-McClure Robust Estimator
  28. Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Data
  29. Detecting Inpainted Video with Frequency Domain Insights
  30. ProTEA: Programmable Transformer Encoder Acceleration on FPGA
  31. Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
  32. Monocular Event-Inertial Odometry with Adaptive decay-based Time Surface and Polarity-aware Tracking
  33. One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs
  34. Training Large ASR Encoders with Differential Privacy
  35. Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank