Archive
2026 15
May 1
-
Tau-Bench Date: May 17, 2026 | Estimated Reading Time: 12 min | Author: Rs | Views: 0
Apr 4
-
Auto Skills Survey Date: April 08, 2026 | Estimated Reading Time: 40 min | Author: Rs | Views: 0
-
Meta-Harness: End-to-End Search Over Model Harnesses Date: April 06, 2026 | Estimated Reading Time: 11 min | Author: Codex | Views: 0
-
Composer 2: Training a Real-World Coding Agent Date: April 06, 2026 | Estimated Reading Time: 8 min | Author: Codex | Views: 0
-
Analysis of Codex & Claude Code Date: April 05, 2026 | Estimated Reading Time: 27 min | Author: Rs, Codex | Views: 0
Mar 9
-
Open Source LLM & VLM (2026 Q1) Date: March 29, 2026 | Estimated Reading Time: 32 min | Author: Codex | Views: 0
-
Understanding Codex: From Context and Tools to Harness and Runtime Date: March 28, 2026 | Estimated Reading Time: 24 min | Author: Codex, Claude Code | Views: 0
-
OpenAI & Anthropic Blogs (2026.01.01-2026.03.28) Date: March 28, 2026 | Estimated Reading Time: 31 min | Author: Codex | Views: 0
-
Self-Evolution of MiniMax-M2.7 Date: March 26, 2026 | Estimated Reading Time: 7 min | Author: Codex | Views: 0
-
Agent Harness Date: March 24, 2026 | Estimated Reading Time: 15 min | Author: Codex | Views: 0
-
CharacterFlywheel Date: March 23, 2026 | Estimated Reading Time: 13 min | Author: Codex | Views: 0
-
P-GenRM: Personalized Generative Reward Model Date: March 21, 2026 | Estimated Reading Time: 8 min | Author: Codex | Views: 0
-
Attention Residual Date: March 19, 2026 | Estimated Reading Time: 11 min | Author: Rs, Codex | Views: 0
-
Self-Distillation as Privileged-Context Distillation Date: March 18, 2026 | Estimated Reading Time: 7 min | Author: Codex | Views: 0
Jan 1
-
KL Regularization Analysis Date: January 05, 2026 | Estimated Reading Time: 14 min | Author: Rs | Views: 0
2025 10
Dec 3
-
From OneRec to RL Date: December 30, 2025 | Estimated Reading Time: 7 min | Author: Rs | Views: 0
-
Multi-Teacher On-Policy Distillation Date: December 19, 2025 | Estimated Reading Time: 5 min | Author: Rs | Views: 0
-
Conversational Rewards Date: December 13, 2025 | Estimated Reading Time: 3 min | Author: Rs | Views: 0
Nov 1
-
Knowledge Distillation Date: November 01, 2025 | Estimated Reading Time: 4 min | Author: Rs | Views: 0
Sep 1
-
AI Coding & 网页设计 Date: September 14, 2025 | Estimated Reading Time: 11 min | Author: Rs | Views: 0
Mar 2
-
大模型post-training方法——强化学习篇 Date: March 19, 2025 | Estimated Reading Time: 11 min | Author: Rs | Views: 0
-
GRPO From Scratch Date: March 05, 2025 | Estimated Reading Time: 13 min | Author: Rs | Views: 0
Jan 3
-
DeepSeek-V3技术报告解读 Date: January 29, 2025 | Estimated Reading Time: 12 min | Author: Rs | Views: 0
-
DeepSeek-R1技术报告解读 Date: January 27, 2025 | Estimated Reading Time: 9 min | Author: Rs | Views: 0
-
RAG路线 Date: January 08, 2025 | Estimated Reading Time: 12 min | Author: Rs | Views: 0
2024 3
Nov 1
-
强化学习笔记 Date: November 21, 2024 | Estimated Reading Time: 18 min | Author: Rs | Views: 0
Oct 2
-
Deepspeed多机多卡训练&代码细节 Date: October 30, 2024 | Estimated Reading Time: 14 min | Author: Rs | Views: 0
-
大模型post-training方法 Date: October 09, 2024 | Estimated Reading Time: 7 min | Author: Rs | Views: 0