Zhangzhe's Blog

09-19

Qwen3-Next：迈向更极致的训练推理性价比

09-09

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

08-10

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

07-15

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

07-13

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

07-04

Toolformer: Language Models Can Teach Themselves to Use Tools

07-04

ReAct: Synergizing Reasoning and Acting in Language Models

07-01

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

05-05

Qwen3 技术报告先导篇

03-17

Transformers without Normalization