🚀 Excited to share our new GitHub repo featuring must-read papers & blogs on Efficient Transformers, Length Extrapolation, Long Term Memory, Retrieval Augmented Generation (RAG), and Evaluation for Long Context Modeling! 🌟🔥 📚 [github.com/Xnhyacinth/Awe…]

[1/n] Super excited to introduce our comprehensive survey on Long Context Language Models (LCLM), a collaborative effort between amazing researchers from Nanjing University , Peking University , CASIA, Alibaba Group , ByteDance , Tencent 腾讯 & Kuaishou! 🚀 Our survey covers 3 core

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild Zero RL training is evaluated across 10 base models using rule-based rewards. Key strategies improve reasoning and response length, with model-specific dynamics and “aha moments”