AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2659
延迟
—
最新内容
当前时间
安全连接 OPERATIONAL

03 / ARTICLE LEDGER

关联文章

按发布时间倒序

  1. AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning 2026-02-27 · ARXIV
  2. Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive 2026-02-27 · ARXIV
  3. A Model-Free Universal AI 2026-02-27 · ARXIV
  4. Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets 2026-02-26 · ARXIV
  5. Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes 2026-02-26 · ARXIV
  6. LiCQA : A Lightweight Complex Question Answering System 2026-02-26 · ARXIV
  7. Improving Parametric Knowledge Access in Reasoning Language Models 2026-02-26 · ARXIV
  8. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL 2026-02-26 · ARXIV
  9. DySCO: Dynamic Attention-Scaling Decoding for Long-Context LMs 2026-02-26 · ARXIV
  10. TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition 2026-02-26 · ARXIV
  11. Neural solver for Wasserstein Geodesics and optimal transport dynamics 2026-02-26 · ARXIV
  12. Function-Space Empirical Bayes Regularisation with Student's t Priors 2026-02-26 · ARXIV
  13. Enhancing LLM-Based Test Generation by Eliminating Covered Code 2026-02-26 · ARXIV
  14. CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models 2026-02-26 · ARXIV
  15. A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT 2026-02-26 · ARXIV
  16. Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training 2026-02-25 · ARXIV
  17. Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking 2026-02-25 · ARXIV
  18. The Diffusion Duality, Chapter II: $Ψ$-Samplers and Efficient Curriculum 2026-02-25 · ARXIV
  19. Test-Time Training with KV Binding Is Secretly Linear Attention 2026-02-25 · ARXIV
  20. Statistical Query Lower Bounds for Smoothed Agnostic Learning 2026-02-25 · ARXIV
  21. Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics 2026-02-25 · ARXIV
  22. On Data Engineering for Scaling LLM Terminal Capabilities 2026-02-25 · ARXIV
  23. Multi-Vector Index Compression in Any Modality 2026-02-25 · ARXIV
  24. Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs 2026-02-25 · ARXIV
  25. Aletheia tackles FirstProof autonomously 2026-02-25 · ARXIV
  26. VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation 2026-02-25 · ARXIV
  27. Tool Building as a Path to "Superintelligence" 2026-02-25 · ARXIV
  28. Scaling Vision Transformers: Evaluating DeepSpeed for Image-Centric Workloads 2026-02-25 · ARXIV
  29. ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learning 2026-02-25 · ARXIV
  30. Motivation is Something You Need 2026-02-25 · ARXIV
  31. Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning 2026-02-25 · ARXIV
  32. Beyond the Star Rating: A Scalable Framework for Aspect-Based Sentiment Analysis Using LLMs and Text Classification 2026-02-25 · ARXIV
  33. An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems 2026-02-25 · ARXIV
  34. Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks 2026-02-24 · ARXIV
  35. KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration 2026-02-24 · ARXIV
  36. JUCAL: Jointly Calibrating Aleatoric and Epistemic Uncertainty in Classification Tasks 2026-02-24 · ARXIV
  37. Conformal Risk Control for Non-Monotonic Losses 2026-02-24 · ARXIV
  38. Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data 2026-02-24 · ARXIV
  39. Agentic AI for Scalable and Robust Optical Systems Control 2026-02-24 · ARXIV
  40. AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization 2026-02-24 · ARXIV
  41. A Very Big Video Reasoning Suite 2026-02-24 · ARXIV
  42. Recurrent Structural Policy Gradient for Partially Observable Mean Field Games 2026-02-24 · ARXIV
  43. Training-Free Cross-Architecture Merging for Graph Neural Networks 2026-02-24 · ARXIV
  44. Soft Sequence Policy Optimization: Bridging GMPO and SAPO 2026-02-24 · ARXIV
  45. Smooth Gate Functions for Soft Advantage Policy Optimization 2026-02-24 · ARXIV
  46. RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework 2026-02-24 · ARXIV
  47. Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence 2026-02-24 · ARXIV
  48. City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification 2026-02-24 · ARXIV
  49. Unifying approach to uniform expressivity of graph neural networks 2026-02-23 · ARXIV
  50. The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning 2026-02-23 · ARXIV