Foundational research for production AI

Our research areas

• Inference
  Design and optimization of production inference systems, spanning scheduling, batching, and hardware–software co-design for reliable high throughput.
  Read papers

• Kernels
  Development of high-performance GPU kernels for training and inference, optimizing memory, attention, and custom operators at production scale.
  Read papers

• Model Shaping
  Advancement of post-training methods like fine-tuning, distillation, and quantization to shape efficient, controllable model behavior.
  Read papers

• Agents
  Studies of long-horizon reasoning and decision-making, focusing on tool use, multi-step planning, and reinforcement learning for reliable agentic systems.
  Read papers

Recognized research

Papers accepted at top conferences

ICML

• DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
  Fan Nie, Junlin Wang, Harper Hua, Federico Bianchi et al.
  Read More

• ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
  Hao Kang, Ziyang Li, Weili Xu, Xinyu Yang, Yinfang Chen et al.
  Read More

• Learning to Discover at Test Time (TTT-Discover)
  Mert Yuksekgonul, Daniel Koceja, Xinhao Li, Federico Bianchi et al.
  Read More

• Escaping the Verifier: Learning to Reason via Demonstrations (RARO)
  Locke Cai, Max Ryabinin, Ivan Provilkov
  Read More

• V1: Unifying Generation and Self-Verification for Parallel Reasoners
  Harman Singh, Xiuyu Li, Kusha Sareen et al.
  Read More

• When RL Meets Adaptive Speculative Training: A Unified Training-Serving System (Aurora)
  Junxiong Wang, Fengxiang Bie, Jisen Li, Zhongzhu Zhou et al.
  Read More

• Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
  Ravi Ghadia, Maksim Abraham, Sergei Vorobyov, Max Ryabinin
  Read More

• Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining (OEA)
  Costin-Andrei Oncescu, Qingyang Wu, Wai Tong Chung et al.
  Read More

• ParallelKernelBench: Benchmarking LLMs on Multi-GPU Kernel Generation
  Willy Chan, Nathan Paek, Simon Guo, Simran Arora, Daniel Y. Fu.
  Read More

Spotlight · ICLR

• ThunderKittens: Simple, Fast, and Adorable AI Kernels
  Benjamin F. Spector, Simran Arora, Aaryan Singhal, Daniel Y. Fu et al.
  Read More

Outstanding Paper · COLM

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
  Albert Gu, Tri Dao
  Read More

Best Paper · ICML HAET

• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
  Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré
  Read More

Oral · ICLR

• Mamba-3: Improved Sequence Modeling using State Space Principles
  Aakash Lahoti, Kevin Y. Li, Berlin Chen, Caitlin Wang, Aviv Bick et al.
  Read More

Key open-source projects

• FlashAttention
  IO-aware exact attention, universally adopted
  Read More

• Flash Decoding
  8× faster long-context token generation
  Read More

• Mixture of Agents
  Open models, working together, beat GPT-4o
  Read More

• Dragonfly
  Tiny 8B model beats Med-Gemini on every benchmark
  Read More

• Red Pajama Datasets
  100T+ tokens powering 500+ models
  Read More

• DeepCoder
  First open model to match o3-mini on code
  Read More

• Open Deep Research
  Open-source multi-model deep research agent
  Read More

• Open Data Scientist Agent
  Autonomous agent tops Adyen's real-world benchmark
  Read More

Featured talks and conference presentations by our researchers

• At Slush 2025, Together AI VP of Kernels Dan Fu dives into building, using, and managing AI agents.
  (Video available)

Research team

Researchers and engineers pushing the boundaries of AI

• Ce Zhang - Founder & CTO
• Chris Ré - Founder
• Tri Dao - Founder & Chief Scientist
• Percy Liang - Founder
• Ben Athiwaratkun - Core ML
• Dan Fu - Kernels
• James Zou - Frontier Agents
• Max Ryabinin - Model Shaping
• Simran Arora - Kernels
• Yineng Zhang - Inference