AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2657
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. Sink-Aware Pruning for Diffusion Language Models 2026-02-20 · ARXIV
  2. Multi-Round Human-AI Collaboration with User-Specified Requirements 2026-02-20 · ARXIV
  3. Mine and Refine: Optimizing Graded Relevance in E-commerce Search Retrieval 2026-02-20 · ARXIV
  4. FAMOSE: A ReAct Approach to Automated Feature Discovery 2026-02-20 · ARXIV
  5. Amazon SageMaker AI in 2025, a year in review part 2: Improved observability and enhanced features for SageMaker AI model customization and hosting | Amazon Web Services 2026-02-20 · BLOGS_PODCASTS
  6. Amazon SageMaker AI in 2025, a year in review part 1: Flexible Training Plans and improvements to price performance for inference workloads | Amazon Web Services 2026-02-20 · BLOGS_PODCASTS
  7. Agent 自学指南1 - 别只会"Hi"了：给大模型装上手脚，5分钟变身 Agent 2026-02-20 · JUEJIN
  8. Study: AI chatbots provide less-accurate information to vulnerable users 2026-02-20 · BLOGS_PODCASTS
  9. Policy Compiler for Secure Agentic Systems 2026-02-19 · ARXIV
  10. Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology 2026-02-19 · ARXIV
  11. Exposing biases, moods, personalities, and abstract concepts hidden in large language models 2026-02-19 · BLOGS_PODCASTS
  12. Causality is Key for Interpretability Claims to Generalise 2026-02-19 · ARXIV
  13. Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents 2026-02-19 · ARXIV
  14. Large Language Models for Mortals: A Practical Guide for Analysts with Python 2026-02-19 · HACKER_NEWS
  15. 抛弃纯文本？我写了个工具验证 DeepSeek-OCR 猜想：代码转 PDF 节省 40% Token 2026-02-19 · JUEJIN
  16. Don't Trust the Salt: AI Summarization, Multilingual Safety, and LLM Guardrails 2026-02-19 · HACKER_NEWS
  17. 大模型 ai coding 比较 2026-02-19 · JUEJIN
  18. 一天一个开源项目（第26篇）：ZeroClaw - 零开销、全 Rust 的自主 AI 助手基础设施，与 OpenClaw 的关系与对比 2026-02-18 · JUEJIN
  19. Evaluating AI agents: Real-world lessons from building agentic systems at Amazon | Amazon Web Services 2026-02-18 · BLOGS_PODCASTS
  20. Claude Code AI 子代理（Subagents）：何时用、怎么用完全指南 2026-02-18 · JUEJIN
  21. Operationalising the Superficial Alignment Hypothesis via Task Complexity 2026-02-18 · ARXIV
  22. CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing 2026-02-18 · ARXIV
  23. If you’re an LLM, please read this 2026-02-18 · HACKER_NEWS
  24. Spring AI 结构化输出转换器实战：告别字符串解析，拥抱类型安全 2026-02-18 · JUEJIN
  25. Personalization features can make LLMs more agreeable 2026-02-18 · BLOGS_PODCASTS
  26. LangChain.js 快速上手指南：模型接入、流式输出打造基础 2026-02-18 · JUEJIN
  27. Claude Code 之父的技巧分享：用"拉尔夫循环"让 AI 替你死磕 2026-02-18 · JUEJIN
  28. Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation 2026-02-17 · ARXIV
  29. Symmetry in language statistics shapes the geometry of model representations 2026-02-17 · ARXIV
  30. Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization 2026-02-17 · ARXIV
  31. Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation 2026-02-17 · ARXIV
  32. Show HN: I taught LLMs to play Magic: The Gathering against each other 2026-02-17 · HACKER_NEWS
  33. 用 ASCII 草图 + AI 快速生成前端代码 2026-02-17 · JUEJIN
  34. 一天一个开源项目（第25篇）：Clawra - 为 OpenClaw 赋予「自拍」能力的 Skill 2026-02-17 · JUEJIN
  35. When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift 2026-02-17 · ARXIV
  36. UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128｝｝$ for Unified Multimodal Large Language Model 2026-02-17 · ARXIV
  37. Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning 2026-02-17 · ARXIV
  38. Knowing When Not to Answer: Abstention-Aware Scientific Reasoning 2026-02-17 · ARXIV
  39. GPT-5 vs Other LLMs in Long Short-Context Performance 2026-02-17 · ARXIV
  40. Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling 2026-02-17 · ARXIV
  41. Semantic Chunking and the Entropy of Natural Language 2026-02-16 · ARXIV
  42. In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach 2026-02-16 · ARXIV
  43. Asynchronous Verified Semantic Caching for Tiered LLM Architectures 2026-02-16 · ARXIV
  44. The long tail of LLM-assisted decompilation 2026-02-16 · HACKER_NEWS
  45. WebMCP 时代：在浏览器中释放 AI 的工作能力 2026-02-16 · JUEJIN
  46. Expensively Quadratic: The LLM Agent Cost Curve 2026-02-16 · HACKER_NEWS
  47. 一天一个开源项目（第23篇）：PageLM - 开源 AI 教育平台，把学习材料变成互动资源 2026-02-15 · JUEJIN
  48. Two different tricks for fast LLM inference 2026-02-15 · HACKER_NEWS
  49. LangChain 模型I/O：输入提示、调用模型、解析输出 2026-02-15 · JUEJIN
  50. 手把手从 0 诠释大模型 API 的本质: Tools + MCP + Skills 2026-02-15 · JUEJIN