mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 25 Feb 2024

128 papers

  1. Evaluating Robustness of Generative Search Engine on Adversarial Factual QuestionsRetrieval-augmented generation → Privacy and security of RAG
  2. Reinforcement Learning Jazz Improvisation: When Music Meets Game TheoryDeep reinforcement learning methods → RL for games and combinatorial optimization
  3. Bootstrapping Cognitive Agents with a Large Language ModelLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  4. DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM JailbreakersLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  5. Diffusion Posterior Proximal Sampling for Image RestorationDiffusion models → Inverse problems and image restoration
  6. Photon-counting CT using a Conditional Diffusion Model for Super-resolution and Texture-preservationDiffusion models → Medical imaging and segmentation
  7. HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  8. Defending Large Language Models against Jailbreak Attacks via Semantic SmoothingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  9. No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design ChoicesLLM safety and security → Watermarking generated content and models
  10. Hitting "Probe"rty with Non-Linearity, and MoreMechanistic interpretability → Knowledge and representations inside LLMs
  11. Cinematographic Camera Diffusion ModelDiffusion models → Video generation
  12. Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy DiffusionDiffusion models → Diffusion and flow policies for robotics +1
  13. Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding BridgeMultimodal LLMs / vision-language models → Video understanding with MLLMs
  14. How Likely Do LLMs with CoT Mimic Human Reasoning?LLM reasoning → Prompting and chain-of-thought reasoning
  15. Don't Forget Your Reward Values: Language Model Alignment via Value-based CalibrationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  16. GraphWiz: An Instruction-Following Language Model for Graph ProblemsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  17. ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix EmbeddingsLLM safety and security → Jailbreaking
  18. Model Compression Method for S4 with Diagonal State Space Layers using Balanced TruncationState-space sequence models (S4, Mamba) → Core SSM architectures for language
  19. Budget-Constrained Tool Learning with PlanningLLM agents and tool use → Tool learning and function calling
  20. DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  21. State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey
  22. RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records
  23. UrbanGPT: Spatio-Temporal Large Language Models
  24. LoRA Meets Dropout under a Unified Framework
  25. Cognitive Bias in Decision-Making with LLMs
  26. EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration
  27. Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale
  28. Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
  29. More Than Routing: Joint GPS and Route Modeling for Refine Trajectory Representation Learning
  30. PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations
  31. An Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection
  32. Trustworthy Personalized Bayesian Federated Learning via Posterior Fine-Tune
  33. NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification
  34. Impact of Physical Activity on Quality of Life During Pregnancy: A Causal ML Approach
  35. Lightweight, error-tolerant edge detection using memristor-enabled stochastic logics
  36. Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
  37. Integrating Preprocessing Methods and Convolutional Neural Networks for Effective Tumor Detection in Medical Imaging
  38. IR2: Information Regularization for Information Retrieval
  39. Language Models for Code Completion: A Practical Evaluation
  40. Combining Machine Learning with Computational Fluid Dynamics using OpenFOAM and SmartSim
  41. ASEM: Enhancing Empathy in Chatbot through Attention-based Sentiment and Emotion Modeling
  42. One-stage Prompt-based Continual Learning
  43. ARIN: Adaptive Resampling and Instance Normalization for Robust Blind Inpainting of Dunhuang Cave Paintings
  44. Deep Neural Network Initialization with Sparsity Inducing Activations
  45. MoodCapture: Depression Detection Using In-the-Wild Smartphone Images
  46. How Can LLM Guide RL? A Value-Based Approach
  47. XAI-based gait analysis of patients walking with Knee-Ankle-Foot orthosis using video cameras
  48. GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
  49. Communication Traffic Characteristics Reveal an IoT Devices Identity
  50. Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation
  51. DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
  52. Distribution-Free Fair Federated Learning with Small Samples
  53. Consensus learning: A novel decentralised ensemble learning paradigm
  54. ChatMusician: Understanding and Generating Music Intrinsically with LLM
  55. From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility
  56. PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
  57. What Generative Artificial Intelligence Means for Terminological Definitions
  58. LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting
  59. A VAE-based Framework for Learning Multi-Level Neural Granger-Causal Connectivity
  60. A statistical method for crack pre-detection in 3D concrete images
  61. AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generation
  62. InstructEdit: Instruction-based Knowledge Editing for Large Language Models
  63. Towards Accurate Post-training Quantization for Reparameterized Models
  64. DeepForge: Leveraging AI for Microstructural Control in Metal Forming via Model Predictive Control
  65. RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
  66. Knowledge Fusion of Chat LLMs: A Preliminary Technical Report
  67. Towards Automated Knowledge Integration From Human-Interpretable Representations
  68. Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
  69. StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention
  70. Bayesian Neural Network For Personalized Federated Learning Parameter Selection
  71. Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis
  72. Deep Homography Estimation for Visual Place Recognition
  73. Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
  74. Equivariant Frames and the Impossibility of Continuous Canonicalization
  75. Pfeed: Generating near real-time personalized feeds using precomputed embedding similarities
  76. ROS-Causal: A ROS-based Causal Analysis Framework for Human-Robot Interaction Applications
  77. Training a Bilingual Language Model by Mapping Tokens onto a Shared Character Space
  78. Citation-Enhanced Generation for LLM-based Chatbots
  79. How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
  80. Gradient-enhanced deep Gaussian processes for multifidelity modelling
  81. Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
  82. Maximizing UAV Fog Deployment Efficiency for Critical Rescue Operations
  83. Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
  84. EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries
  85. Understanding Public Perceptions of AI Conversational Agents: A Cross-Cultural Analysis
  86. Deep Learning Approaches for Improving Question Answering Systems in Hepatocellular Carcinoma Research
  87. Machine Learning-Based Vehicle Intention Trajectory Recognition and Prediction for Autonomous Driving
  88. Text Understanding and Generation Using Transformer Models for Intelligent E-commerce Recommendations
  89. Emotion Classification in Short English Texts using Deep Learning Techniques
  90. Exploiting Regional Information Transformer for Single Image Deraining
  91. Feature Selection Based on Orthogonal Constraints and Polygon Area
  92. HiGPT: Heterogeneous Graph Language Model
  93. TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages
  94. A Step-by-step Introduction to the Implementation of Automatic Differentiation
  95. Spectrum Extraction and Clipping for Implicitly Linear Layers
  96. OmniArch: Building Foundation Model For Scientific Computing
  97. Semi-supervised Open-World Object Detection
  98. Deep Contrastive Graph Learning with Clustering-Oriented Guidance
  99. PST-Bench: Tracing and Benchmarking the Source of Publications
  100. Unmasking Dementia Detection by Masking Input Gradients: A JSM Approach to Model Interpretability and Precision
All 128
  1. Adversarial-Robust Transfer Learning for Medical Imaging via Domain Assimilation
  2. Post-Quantum Cryptography Neural Network
  3. Cross-Resolution Land Cover Classification Using Outdated Products and Transformers
  4. Cieran: Designing Sequential Colormaps via In-Situ Active Preference Learning
  5. Improved Hardness Results for Learning Intersections of Halfspaces
  6. Optimizing Portfolio Management and Risk Assessment in Digital Assets Using Deep Learning for Predictive Analysis
  7. A Machine Learning Approach to Detect Customer Satisfaction From Multiple Tweet Parameters
  8. C3: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding
  9. An Empirical Study of Challenges in Machine Learning Asset Management
  10. PIDformer: Transformer Meets Control Theory
  11. Towards Fair Graph Anomaly Detection: Problem, Benchmark Datasets, and Evaluation
  12. Likelihood-based Mitigation of Evaluation Bias in Large Language Models
  13. Phonetic and Lexical Discovery of a Canine Language using HuBERT
  14. A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks
  15. Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood
  16. Capsule Endoscopy Image Enhancement for Small Intestinal Villi Clarity
  17. Structural Knowledge-Driven Meta-Learning for Task Offloading in Vehicular Networks with Integrated Communications, Sensing and Computing
  18. CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models
  19. Direct Punjabi to English speech translation using discrete units
  20. Hierarchical energy signatures using machine learning for operational visibility and diagnostics in automotive manufacturing
  21. VOLoc: Visual Place Recognition by Querying Compressed Lidar Map
  22. Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
  23. On the dynamics of three-layer neural networks: initial condensation
  24. ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis
  25. DetoxLLM: A Framework for Detoxification with Explanations
  26. Attention-GAN for Anomaly Detection: A Cutting-Edge Approach to Cybersecurity Threat Management
  27. Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
  28. Implementing Recycling Methods for Linear Systems in Python with an Application to Multiple Objective Optimization