Research blog

Inference

AdapTive-LeArning Speculator System (ATLAS): A New Paradigm in LLM Inference via Runtime-Learning Accelerators

ATLAS delivers up to 4x faster LLM inference, powered by Together Turbo’s latest research.

Junxiong Wang, Shirley Wu, Zelei Shao, Vikranth Srivatsa, Jue Wang, Roy Yuan, Qingyang Wu, Alpay Ariyak, Rupert Wu, Wai Tong Chung, Chenfeng Xu, Yonatan Oren, Pragaash Ponnusamy, Yineng Zhang, Avner May, Leon Song, Tri Dao, Percy Liang, Ce Zhang, Ben Athiwaratkun

Agents

How Together AI Uses AI Agents to Automate Complex Engineering Tasks: Lessons from Developing Efficient LLM Inference Systems

Shang Zhu, Federico Bianchi, Wai Tong Chung, Zain Hasan, Rupert Wu, Ce Zhang, James Zou, Ben Athiwaratkun

Agents

Back to The Future: Evaluating AI Agents on Predicting Future Events

Federico Bianchi, Junlin Wang, Zain Hasan, Shang Zhu, Roy Yuan, Clémentine Fourrier, James Zou

Retro futuristic scene with a DeLorean car, neon grid floor, mountains, and a striped glowing sun.

Inference

DeepSWE: Training a Fully Open-sourced, State-of-the-Art Coding Agent by Scaling RL

Michael Luo*, Naman Jain*, Jaskirat Singh*, Sijun Tan*, Ameen Patel*, Qingyang Wu*, Alpay Ariyak*, Colin Cai*, Tarun Venkat, Shang Zhu, Ben Athiwaratkun, Manan Roongta, Ce Zhang, Li Erran Li, Raluca Ada Popa, Koushik Sen, Ion Stoica

Chart showing SWE-Bench performance vs model size for various models with DeepSWE-Preview + TTS leading at 59%.

No search result

Try expanding your search or changing the filters.