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. 如何用 AI 做业务级 Code Review 2026-02-27 · JUEJIN
  2. Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments 2026-02-27 · ARXIV
  3. Mitigating Legibility Tax with Decoupled Prover-Verifier Games 2026-02-27 · ARXIV
  4. Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems 2026-02-27 · ARXIV
  5. Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive 2026-02-27 · ARXIV
  6. 灵感启发：日产文章 100 篇，打造“实时热点洞察”引擎 2026-02-26 · JUEJIN
  7. Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets 2026-02-26 · ARXIV
  8. Large model inference container – latest capabilities and performance enhancements | Amazon Web Services 2026-02-26 · BLOGS_PODCASTS
  9. New method could increase LLM training efficiency 2026-02-26 · BLOGS_PODCASTS
  10. crawl4ai：AI时代的数据采集利器——从入门到实战 2026-02-26 · JUEJIN
  11. Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts 2026-02-26 · HACKER_NEWS
  12. Enhancing LLM-Based Test Generation by Eliminating Covered Code 2026-02-26 · ARXIV
  13. CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models 2026-02-26 · ARXIV
  14. Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training 2026-02-25 · ARXIV
  15. On Data Engineering for Scaling LLM Terminal Capabilities 2026-02-25 · ARXIV
  16. Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs 2026-02-25 · ARXIV
  17. Large-Scale Online Deanonymization with LLMs 2026-02-25 · HACKER_NEWS
  18. AI Agent框架探秘：拆解 OpenHands（8）--- CodeActAgent 2026-02-25 · JUEJIN
  19. VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation 2026-02-25 · ARXIV
  20. Tool Building as a Path to "Superintelligence" 2026-02-25 · ARXIV
  21. Beyond the Star Rating: A Scalable Framework for Aspect-Based Sentiment Analysis Using LLMs and Text Classification 2026-02-25 · ARXIV
  22. An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems 2026-02-25 · ARXIV
  23. Mercury 2: Fast reasoning LLM powered by diffusion 2026-02-25 · HACKER_NEWS
  24. Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks 2026-02-24 · ARXIV
  25. RCCLX: Innovating GPU Communications on AMD Platforms 2026-02-24 · BLOGS_PODCASTS
  26. KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration 2026-02-24 · ARXIV
  27. Agentic AI for Scalable and Robust Optical Systems Control 2026-02-24 · ARXIV
  28. AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization 2026-02-24 · ARXIV
  29. Train CodeFu-7B with veRL and Ray on Amazon SageMaker Training jobs | Amazon Web Services 2026-02-24 · BLOGS_PODCASTS
  30. Generate structured output from LLMs with Dottxt Outlines in AWS | Amazon Web Services 2026-02-24 · BLOGS_PODCASTS
  31. 聊聊大模型开发的发展历程 2026-02-24 · JUEJIN
  32. 让AI帮我做测试用例，我来喝咖啡 2026-02-24 · JUEJIN
  33. Soft Sequence Policy Optimization: Bridging GMPO and SAPO 2026-02-24 · ARXIV
  34. Smooth Gate Functions for Soft Advantage Policy Optimization 2026-02-24 · ARXIV
  35. Making Wolfram tech available as a foundation tool for LLM systems 2026-02-24 · HACKER_NEWS
  36. SPQ: An Ensemble Technique for Large Language Model Compression 2026-02-23 · ARXIV
  37. Agentic AI with multi-model framework using Hugging Face smolagents on AWS | Amazon Web Services 2026-02-23 · BLOGS_PODCASTS
  38. nano-vllm(1)：大模型推理原理和流程 2026-02-23 · JUEJIN
  39. AI Agent 框架探秘：拆解 OpenHands（7）--- Agent 2026-02-23 · JUEJIN
  40. 你的 nginx 在扼杀 AI 服务——为什么需要重新设计流量层 2026-02-23 · JUEJIN
  41. Show HN: AI Timeline – 171 LLMs from Transformer (2017) to GPT-5.3 (2026) 2026-02-23 · HACKER_NEWS
  42. AGENTS.md 真的对 AI Coding 有用吗？或许在此之前你没用对？ 2026-02-22 · JUEJIN
  43. Go + Eino 构建 AI Agent（二）：Tool Calling 2026-02-22 · JUEJIN
  44. Spring AI MCP 之 SSE WebFlux 实战：从零构建 AI 天气助手 2026-02-22 · JUEJIN
  45. How Taalas “prints” LLM onto a chip? 2026-02-22 · HACKER_NEWS
  46. 04:工具系统设计：从抽象基类到 JSON Schema 的完整实现 2026-02-22 · JUEJIN
  47. 03:多 LLM 提供商统一接入：Provider 模式与 LiteLLM 实践 2026-02-22 · JUEJIN
  48. Claws are now a new layer on top of LLM agents 2026-02-21 · HACKER_NEWS
  49. Large Language Model Reasoning Failures 2026-02-21 · HACKER_NEWS
  50. What Language is This? Ask Your Tokenizer 2026-02-20 · ARXIV