@tydsh Looking to see you!

Dec. 10-Dec. 15 in NeurIPS’24. Our poster will be presented Friday 11 am.See u in Vancouver!

RT @ChengLuo_lc: 🤩🤩 we introduce MST, a memory-efficient transformer, reducing intermediate memory usage and enabling longer sequence train…

Our MST got accepted by NIPS 2024

RT @rohanpaul_ai: Really 👀 new Paper, MINI-SEQUENCE TRANSFORMER claims to extend the maximum context length of Qwen, Mistral, and Gemma-2 b…

RT @papers_anon: Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer Saw a 16x increase in sequence le…

Curious about boosting context length in Llama 3.1 by 16x? 🦙 Our Mini-sequence Transformer (MST) offers insights! 🚀 MST extends context length with no performance drop. 📈 Our paper: and GitHub: #Llama #NLP #AI #llama31

RT @AnimaAnandkumar: Introducing long-context transformer using mini sequences. It is a simple and effective method for highly efficient an…

making my first personal blob: Cheng Luo - Personal Page (

Shanghai Concentration Camp

@SpeechFreedomCN Stand with Ukraine