mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 11 May 2024

100 papers

  1. Survey on Reasoning Capabilities and Accessibility of Large Language Models Using Biology-related QuestionsLLM reasoning → Clinical and biomedical applications
  2. Prompt-guided Precise Audio Editing with Diffusion ModelsDiffusion models → Audio, speech and music
  3. RAGE Against the Machine: Retrieval-Augmented LLM ExplanationsRetrieval-augmented generation → RAG pipeline design and evaluation
  4. Diff-ETS: Learning a Diffusion Probabilistic Model for Electromyography-to-Speech ConversionDiffusion models → Audio, speech and music
  5. AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss WeightingKnowledge distillation → General knowledge distillation methods
  6. Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITALLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  7. Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systemsDiffusion models → Diffusion foundations and sampling
  8. Auditing an Automatic Grading Model with deep Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  9. Integrating Emotional and Linguistic Models for Ethical Compliance in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  10. Semantic Guided Large Scale Factor Remote Sensing Image Super-resolution with Generative Diffusion PriorDiffusion models → Inverse problems and image restoration
  11. DTMamba : Dual Twin Mamba for Time Series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
  12. Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You ThoughtLLM safety and security → Membership inference attacks
  13. Stealthy Imitation: Reward-guided Environment-free Policy StealingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  14. ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question AnsweringMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  15. TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable PromptMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  16. Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor SignalsDeep reinforcement learning methods → Deep RL algorithms and representations
  17. Non-confusing Generation of Customized Concepts in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  18. Fairness in Reinforcement Learning: A SurveyDeep reinforcement learning methods → RL for games and combinatorial optimization
  19. AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI AgentsLLM agents and tool use → Software engineering coding agents
  20. Aladdin: Joint Placement and Scaling for SLO-Aware LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  21. The Silent Curriculum: How Does LLM Monoculture Shape Educational Content and Its Accessibility?
  22. A Robust Governance for the AI Act: AI Office, AI Board, Scientific Panel, and National Authorities
  23. QMViT: A Mushroom is worth 16x16 Words
  24. DeVOS: Flow-Guided Deformable Transformer for Video Object Segmentation
  25. ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency
  26. Translating Expert Intuition into Quantifiable Features: Encode Investigator Domain Knowledge via LLM for Enhanced Predictive Analytics
  27. A Methodology-Oriented Study of Catastrophic Forgetting in Incremental Deep Neural Networks
  28. Robot Detection System 1: Front-Following
  29. CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network
  30. Designing and Evaluating Dialogue LLMs for Co-Creative Improvised Theatre
  31. Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning
  32. Do Pretrained Contextual Language Models Distinguish between Hebrew Homograph Analyses?
  33. Interpretable global minima of deep ReLU neural networks on sequentially separable data
  34. Data-Efficient and Robust Task Selection for Meta-Learning
  35. T-curator: a trust based curation tool for LOD logs
  36. Decoding Cognitive Health Using Machine Learning: A Comprehensive Evaluation for Diagnosis of Significant Memory Concern
  37. Catastrophe Insurance: An Adaptive Robust Optimization Approach
  38. Learning Flame Evolution Operator under Hybrid Darrieus Landau and Diffusive Thermal Instability
  39. LLMs and the Future of Chip Design: Unveiling Security Risks and Building Trust
  40. Length-Aware Multi-Kernel Transformer for Long Document Classification
  41. Solving Energy-Independent Density for CT Metal Artifact Reduction via Neural Representation
  42. RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning
  43. Predictive Modeling in the Reservoir Kernel Motif Space
  44. Multi-agent Traffic Prediction via Denoised Endpoint Distribution
  45. Online Auction Design Using Distribution-Free Uncertainty Quantification with Applications to E-Commerce
  46. A Turkish Educational Crossword Puzzle Generator
  47. A Performance Analysis Modeling Framework for Extended Reality Applications in Edge-Assisted Wireless Networks
  48. Global Motion Understanding in Large-Scale Video Object Segmentation
  49. Lasso Ridge based XGBoost and Deep_LSTM Help Tennis Players Perform better
  50. TD-NeRF: Novel Truncated Depth Prior for Joint Camera Pose and Neural Radiance Field Optimization
  51. Demystifying the Hypercomplex: Inductive Biases in Hypercomplex Deep Learning
  52. Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution
  53. Bayesian Frequency Estimation Under Local Differential Privacy With an Adaptive Randomized Response Mechanism
  54. Incorporating Degradation Estimation in Light Field Spatial Super-Resolution
  55. Fair Graph Representation Learning via Sensitive Attribute Disentanglement
  56. Deciphering public attention to geoengineering and climate issues using machine learning and dynamic analysis
  57. Word-specific tonal realizations in Mandarin
  58. Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT
  59. Benchmarking Cross-Domain Audio-Visual Deception Detection
  60. GRASP-GCN: Graph-Shape Prioritization for Neural Architecture Search under Distribution Shifts
  61. Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations
  62. ResSurv: Cancer Survival Analysis Prediction Model Based on Residual Networks
  63. Revisiting the Efficacy of Signal Decomposition in AI-based Time Series Prediction
  64. RoTHP: Rotary Position Embedding-based Transformer Hawkes Process
  65. AraSpell: A Deep Learning Approach for Arabic Spelling Correction
  66. Fractals as Pre-training Datasets for Anomaly Detection and Localization
  67. Robust Semi-supervised Learning by Wisely Leveraging Open-set Data
  68. Input Snapshots Fusion for Scalable Discrete-Time Dynamic Graph Neural Networks
  69. A Primer for Preferential Non-Monotonic Propositional Team Logics
  70. A Machine Learning-based Approach for Solving Recurrence Relations and its use in Cost Analysis of Logic Programs
  71. A De-singularity Subgradient Approach for the Extended Weber Location Problem
  72. ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots
  73. Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
  74. Direct and Adaptable Mesh-Gaussian Scene Reconstruction from Multi-View Images
  75. Learning Monocular Depth from Focus with Event Focal Stack
  76. Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training
  77. PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
  78. EmoMix-3L: A Code-Mixed Dataset for Bangla-English-Hindi Emotion Detection
  79. Automating Thematic Analysis: How LLMs Analyse Controversial Topics
  80. Super-Resolving Blurry Images with Events
  81. Design Requirements for Human-Centered Graph Neural Network Explanations
  82. High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptation
  83. Automating Creativity
  84. Replication Study and Benchmarking of Real-Time Object Detection Models
  85. Generative flow induced neural architecture search: Towards discovering optimal architecture in wavelet neural operator
  86. Finding structure in logographic writing with library learning
  87. Generation of Granular-Balls for Clustering Based on the Principle of Justifiable Granularity
  88. UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence
  89. Causal Inference from Slowly Varying Nonstationary Processes
  90. ADLDA: A Method to Reduce the Harm of Data Distribution Shift in Data Augmentation
  91. TacoERE: Cluster-aware Compression for Event Relation Extraction
  92. FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment
  93. Event GDR: Event-Centric Generative Document Retrieval
  94. Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
  95. EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation
  96. LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization
  97. eCAR: edge-assisted Collaborative Augmented Reality Framework
  98. Sharpness-Aware Minimization for Evolutionary Feature Construction in Regression
  99. Disrupting Style Mimicry Attacks on Video Imagery
  100. Reimplementation of Learning to Reweight Examples for Robust Deep Learning