Excellent! 704 posts in total. Keep on posting.

NLP——Reasoning2Agentic-Credit-Assignment

NLP——LLM对齐微调-Rethinking-OPD

NLP——ImplicitRM

NLP——Claude模型API-Prompt缓存功能

NLP——Rethinking-Generalization-In-Reasoning-SFT

NLP——LLM对齐微调-Revisiting-OPD

NLP——Why-Self-Distillation-Fails-in-Reasoning

NLP——技术报告解读-Nemotron-Cascade-2

NLP——技术报告解读-Nemotron-Cascade

AGI——林俊旸博客-From-Reasoning-Thinking2Agentic-Thinking