mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 13 Sep 2025

89 papers

  1. OpenHA: A Series of Open-Source Hierarchical Agentic Models in MinecraftLLM agents and tool use → Reinforcement learning for LLM agents
  2. Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic EncodingLLM safety and security → Jailbreaking
  3. Lightweight Metadata-Aware Mixture-of-Experts Masked Autoencoder for Earth ObservationMixture-of-experts → Vision mixture-of-experts
  4. ToMA: Token Merge with Attention for Diffusion ModelsDiffusion models → Diffusion foundations and sampling +1
  5. Robustifying Diffusion-Denoised Smoothing Against Covariate ShiftDiffusion models → Robustness, privacy and adversarial aspects
  6. CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer SynthesisRetrieval-augmented generation → Generation and context integration
  7. Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?LLM agents and tool use → General LLM agent frameworks and benchmarks
  8. Text2Sign Diffusion: A Generative Approach for Gloss-Free Sign Language ProductionDiffusion models → Sign language production
  9. GAPrune: Gradient-Alignment Pruning for Domain-Aware EmbeddingsLLM agents and tool use → Web, search, and research agents
  10. Evaluating Large Language Models for Evidence-Based Clinical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
  11. Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features AloneLLM reasoning → Reasoning benchmarks and evaluation
  12. Judge Q: Trainable Queries for Optimized Information Retention in KV Cache EvictionEfficient LLM inference and serving → KV cache optimization
  13. AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in EnterpriseLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. EditDuet: A Multi-Agent System for Video Non-Linear EditingLLM agents and tool use → Multimodal and embodied agents
  15. Socially Aware Music Recommendation: A Multi-Modal Graph Neural Networks for Collaborative Music Consumption and Community-Based Engagement
  16. CityAQVis: Integrated ML-Visualization Sandbox Tool for Pollutant Estimation in Urban Regions Using Multi-Source Data (Software Article)
  17. Unpacking Musical Symbolism in Online Communities: Content-Based and Network-Centric Approaches
  18. PISA: An AI Pipeline for Interpretable-by-design Survival Analysis Providing Multiple Complexity-Accuracy Trade-off Models
  19. A systematic review of trial-matching pipelines using large language models
  20. Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers
  21. How Much of Your Data Can Suck? Thresholds for Domain Performance and Emergent Misalignment in LLMs
  22. Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing
  23. Refining Syntactic Distinctions Using Decision Trees: A Paper on Postnominal 'That' in Complement vs. Relative Clauses
  24. Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs
  25. Label-Efficient Grasp Joint Prediction with Point-JEPA
  26. A Variational Physics-Informed Neural Network Framework Using Petrov-Galerkin Method for Solving Singularly Perturbed Boundary Value Problems
  27. Research on Short-Video Platform User Decision-Making via Multimodal Temporal Modeling and Reinforcement Learning
  28. A Traditional Approach to Symbolic Piano Continuation
  29. Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models
  30. A Modern Look at Simplicity Bias in Image Classification Tasks
  31. Gradient Methods with Online Scaling Part II. Practical Aspects
  32. AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting
  33. Hardness, Structural Knowledge, and Opportunity: An Analytical Framework for Modular Performance Modeling
  34. Policy-Driven Transfer Learning in Resource-Limited Animal Monitoring
  35. Factor Graph Optimization for Leak Localization in Water Distribution Networks
  36. TrueSkin: Towards Fair and Accurate Skin Tone Recognition and Generation
  37. ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER
  38. Decoupling Search and Learning in Neural Net Training
  39. Enhancing Computational Cognitive Architectures with LLMs: A Case Study
  40. PHLoRA: data-free Post-hoc Low-Rank Adapter extraction from full-rank checkpoint
  41. The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models
  42. Gaze Authentication: Factors Influencing Authentication Performance
  43. Predictive Free Energy Simulations Through Hierarchical Distillation of Quantum Hamiltonians
  44. Testing for LLM response differences: the case of a composite null consisting of semantically irrelevant query perturbations
  45. Simulating Sinogram-Domain Motion and Correcting Image-Domain Artifacts Using Deep Learning in HR-pQCT Bone Imaging
  46. ViSTR-GP: Online Cyberattack Detection via Vision-to-State Tensor Regression and Gaussian Processes in Automated Robotic Operations
  47. When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning
  48. An Interpretable Benchmark for Clickbait Detection and Tactic Attribution
  49. Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents
  50. Public Data Assisted Differentially Private In-Context Learning
  51. Clarifying Model Transparency: Interpretability versus Explainability in Deep Learning with MNIST and IMDB Examples
  52. Aligning ESG Controversy Data with International Guidelines through Semi-Automatic Ontology Construction
  53. TV Subgradient-Guided Multi-Source Fusion for Spectral Imaging in Dual-Camera CASSI Systems
  54. AutoOEP -- A Multi-modal Framework for Online Exam Proctoring
  55. Nav-R1: Reasoning and Navigation in Embodied Scenes
  56. Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies
  57. On the Impact of Downstream Tasks on Sampling and Reconstructing Noisy Graph Signals
  58. Optimal message passing for molecular prediction is simple, attentive and spatial
  59. GTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
  60. Physics-informed neural network solves minimal surfaces in curved spacetime
  61. CogGNN: Cognitive Graph Neural Networks in Generative Connectomics
  62. Quantifier Scope Interpretation in Language Learners and LLMs
  63. Large Language Models for Security Operations Centers: A Comprehensive Survey
  64. Variable Selection Using Relative Importance Rankings
  65. Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
  66. Neurosymbolic AI Transfer Learning Improves Network Intrusion Detection
  67. A funny companion: Distinct neural responses to AI- versus human-attributed humor
  68. OpenUrban3D: Annotation-Free Open-Vocabulary Semantic Segmentation of Large-Scale Urban Point Clouds
  69. Point-Plane Projections for Accurate LiDAR Semantic Segmentation in Small Data Scenarios
  70. A Comparison of Selected Image Transformation Techniques for Malware Classification
  71. Exploring the Paradigm Shift from Grounding to Skolemization for Complex Query Answering on Knowledge Graphs
  72. Towards Automated Error Discovery: A Study in Conversational AI
  73. CUBE: Contrastive Understanding by Balanced Experiments
  74. Multi-Task Diffusion Approach For Prediction of Glioma Tumor Progression
  75. LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering
  76. Well-Conditioned Polynomial Representations for Mathematical Handwriting Recognition
  77. InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
  78. Branched Broomrape Detection in Tomato Farms Using Satellite Imagery and Time-Series Analysis
  79. Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
  80. GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research
  81. Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
  82. Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practices
  83. Group Evidence Matters: Tiling-based Semantic Gating for Dense Object Detection
  84. Contextual Budget Bandit for Food Rescue Volunteer Engagement
  85. RSL-RL: A Learning Library for Robotics Research
  86. Enhancement Without Contrast: Stability-Aware Multicenter Machine Learning for Glioma MRI Imaging
  87. MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks
  88. AI Answer Engine Citation Behavior An Empirical Analysis of the GEO16 Framework
  89. Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation