WAI

@waiorg

Open Agentic Research.

Seattle

固定
WAI
@waiorg
6月22日
We’re thrilled to launch WAI! WAI is a research organization formed by NLP/ML/System PhDs from the University of Washington. We open-source our works on AI agents across the full stack — data, systems, training, and evaluation. Stay tuned! Website: wai-org.com
WAI
@waiorg
11月3日
We have some neat updates to TMax that fix RL collapse and improve data verification! Blog: wai-org.com/blog/tmax-v1-1/
Oscar Yinn
@oscar_yinn
11月3日
Terminalmaxxing cannot be stopped 🤫 Introducing TMax v1.1! We improved our data and infrastructure, and managed to improve our models by up to 6 points on TB2. TMax v1.1 dominates the Pareto curve for open terminal agents under 30B. As usual, we release everything: our
WAI
@waiorg
10月2日
We recently released Context Language Models (CLMs), and got many questions on KV Cache. Our latest blog explains 1). how we measure cache-ware FLOPs 2). how to efficiently serve CLM wai-org.com/blog/clm/
Rulin Shao
@RulinShao
10月2日
AI systems should be designed for AI. If prefix caching gets in the way of free context access, we can fix the caching. This is the idea behind our Suffix Cache Reuse (SCR) for CLR serving. Check out our blogpost for details (fun visuals included)! wai-org.com/blog/clm/
WAI
@waiorg
6月22日
WAI is proud to introduce TMax: open terminal agents trained on an academic budget. Across different model sizes, TMax lies on the Pareto-optimal frontier of terminal-agent performance. Academic-scale RL can really produce highly competitive agents. Check out our Blog! wai-org.com/blog/tmax/
Hamish Ivison
@hamishivi
6月22日
Trained some terminal agents with friends! Introducing Tmax, open RL terminal agent models. Under default settings and shorter length (65k) token budgets, tmax outperforms prior open work on terminal use. We are releasing all data+weights+rollouts publically!
1

WAI

WAIさんのポスト