Together AI at MLSys 2026

May 18-22, 2026
Bellevue, WA

Time to start

Days

Hours

Days

Minutes

Days

Seconds

platinum Sponsor

Join us at MLSys

Where the world’s deep learning community comes to build what’s next: Accelerated compute, production inference, model shaping, and research — all at the frontier of AI.

Join us for an exclusive event

Come unwind after a day at MLSys with drinks, after party bites, shuffleboard, and even better company.
Join fellow researchers and builders shaping what’s next in AI.

Inference After Dark

May 21, 7:30 - 10:00 P.M.

Invite only

Papers we’re presenting at MLSys

research paper
OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents
may 19
1:00 p.m.
Reyna Abhyankar
Sr Systems Research EngineerTogether AI
Yineng Zhang
principal ai researcherTogether AI
View Details
research paper
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
may 20
1:00 p.m.
Jue Wang
Research ScientistTogether AI
Aman Singhal
AI/Ml ResearcherTogether AI
Alay Shah
Senior ML Research EngineerTogether AI
Donglin Zhuang
ResearcherTogether AI
Zhongzhu Zhou
Research ConsultantTogether AI
Ben Athiwaratkun
staff ai/ml researcherTogether AI
Shirley Wu
Senior Staff ScientistTogether AI
Connor Li
Senior ML Operations EngineerTogether AI
View Details
research paper
Search Your NVFP4 Scales!
may 20
poster session 2
Tanmaey Gupta
Research InternTogether AI
Hayden Prairie
Research InternTogether AI
Shirley Wu
Senior Staff ScientistTogether AI
Reyna Abhyankar
Sr Systems Research EngineerTogether AI
Qingyang Wu
Head of Frontier AgentsTogether AI
Austin Silveria
Sr Systems Research EngineerTogether AI
Pragaash Ponnusamy
Principal Ml ResearcherTogether AI
Jue Wang
Research ScientistTogether AI
Ben Athiwaratkun
staff ai/ml researcherTogether AI
Leon Song
VP of ResearchTogether AI
Tri Dao
co-founder & Chief ScientistTogether AI
Daniel Fu
VP of KernelsTogether AI
Christopher De Sa
Research ScientistTogether AI
View Details
research paper
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
may 20
poster session 2
Zelei Shao
ResearcherTogether AI
Vikranth Srivatsa
research internTogether AI
Junxiong Wang
ResearcherTogether AI
Chenfeng Xu
Senior AI ResearcherTogether AI
Shirley Wu
Senior Staff ScientistTogether AI
Qingyang Wu
AI/Ml ResearcherTogether AI
Jue Wang
Research ScientistTogether AI
Ameen Patel
ml engineerTogether AI
Yineng Zhang
principal ai researcherTogether AI
Percy Liang
founderTogether AI
Tri Dao
co-founder & Chief ScientistTogether AI
Ben Athiwaratkun
staff ai/ml researcherTogether AI
Ce Zhang
co-founder & CTOTogether AI
View Details
research paper
CDLM: Consistency Diffusion Language Models for faster sampling
may 21
8:30 A.m.
Chenfeng Xu
Senior AI ResearcherTogether AI
Ben Athiwaratkun
staff ai/ml researcherTogether AI
Ce Zhang
co-founder & CTOTogether AI
View Details
research paper
ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
may 21
poster session 3
Stuart H. Sul
ML researcherCursor
Simran Arora
Principal ScientistTogether AI
Benjamin Spector
research internTogether AI
Christopher Ré
founderTogether AI
View Details
research paper
FlashAttention-4
may 22
8:30 A.m.
Ted Zadouri
research internTogether AI
Markus Hoehnerbach
senior software engineerTogether AI
Jay Shah
research scientistTogether AI
Timmy Liu
nvidia
Vijay Thakkar
ai research scientistMeta
Tri Dao
Co-Founder & Chief ScientistTogether AI
View Details