AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
3101
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. Automated Reasoning checks rewriting chatbot reference implementation | Amazon Web Services 2026-02-10 · BLOGS_PODCASTS
  2. ARO: A New Lens On Matrix Optimization For Large Models 2026-02-10 · ARXIV
  3. LangChain 进阶实战：当 Memory 遇上 OutputParser，打造有记忆的结构化助手 2026-02-10 · JUEJIN
  4. ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling 2026-02-10 · ARXIV
  5. Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model 2026-02-10 · ARXIV
  6. MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation 2026-02-10 · ARXIV
  7. Emergent Misalignment is Easy, Narrow Misalignment is Hard 2026-02-10 · ARXIV
  8. Learning a Generative Meta-Model of LLM Activations 2026-02-09 · ARXIV
  9. Endogenous Resistance to Activation Steering in Language Models 2026-02-09 · ARXIV
  10. DAWN: Dependency-Aware Fast Inference for Diffusion LLMs 2026-02-09 · ARXIV
  11. LLMs as the new high level language 2026-02-08 · HACKER_NEWS
  12. Experts Have World Models. LLMs Have Word Models 2026-02-07 · HACKER_NEWS
  13. Evaluating and mitigating the growing risk of LLM-discovered 0-days 2026-02-07 · HACKER_NEWS
  14. PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling 2026-02-06 · ARXIV
  15. Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory 2026-02-06 · ARXIV
  16. DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching 2026-02-06 · ARXIV
  17. DFlash: Block Diffusion for Flash Speculative Decoding 2026-02-06 · ARXIV
  18. CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction 2026-02-06 · ARXIV
  19. Show HN: BioTradingArena – Benchmark for LLMs to predict biotech stock movements 2026-02-06 · HACKER_NEWS
  20. LLMs could be, but shouldn't be compilers 2026-02-06 · HACKER_NEWS
  21. RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference 2026-02-06 · ARXIV
  22. DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders 2026-02-06 · ARXIV
  23. Subliminal Effects in Your Data: A General Mechanism via Log-Linearity 2026-02-05 · ARXIV
  24. Rethinking the Trust Region in LLM Reinforcement Learning 2026-02-05 · ARXIV
  25. Reinforced Attention Learning 2026-02-05 · ARXIV
  26. Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism 2026-02-05 · ARXIV
  27. CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation 2026-02-05 · ARXIV
  28. AstrBotDevs/AstrBot 2026-02-05 · GITHUB_TRENDING
  29. Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL 2026-02-04 · ARXIV
  30. Accelerating Scientific Research with Gemini: Case Studies and Common Techniques 2026-02-04 · ARXIV
  31. Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability 2026-02-03 · ARXIV
  32. RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System 2026-02-03 · ARXIV
  33. Reward-free Alignment for Conflicting Objectives 2026-02-03 · ARXIV
  34. RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents 2026-02-03 · ARXIV
  35. MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents 2026-02-03 · ARXIV
  36. Expanding the Capabilities of Reinforcement Learning via Text Feedback 2026-02-03 · ARXIV
  37. AgentRx: Diagnosing AI Agent Failures from Execution Trajectories 2026-02-03 · ARXIV
  38. Show HN: I built "AI Wattpad" to eval LLMs on fiction 2026-02-03 · HACKER_NEWS
  39. Sparse Reward Subsystem in Large Language Models 2026-02-03 · ARXIV
  40. Reliable Use of Lemmas via Eligibility Reasoning and Section$-$Aware Reinforcement Learning 2026-02-03 · ARXIV
  41. Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning 2026-02-03 · ARXIV
  42. How RLHF Amplifies Sycophancy 2026-02-03 · ARXIV
  43. Error Taxonomy-Guided Prompt Optimization 2026-02-03 · ARXIV
  44. UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection 2026-02-02 · ARXIV
  45. TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training 2026-02-02 · ARXIV
  46. FOCUS: DLLMs Know How to Tame Their Compute Bound 2026-02-02 · ARXIV
  47. My iPhone 16 Pro Max produces garbage output when running MLX LLMs 2026-02-02 · HACKER_NEWS
  48. Safer Policy Compliance with Dynamic Epistemic Fallback 2026-02-02 · ARXIV
  49. OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning 2026-02-02 · ARXIV
  50. From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching 2026-02-02 · ARXIV