📣 I'm thrilled to share that I’ll be joining MIT as an assistant professor this fall, joint between MIT Media Lab & MIT EECS. My group will advance the foundations of multisensory AI to enhance the human experience. I look forward to tackling exciting challenges in multimodal AI

New NeurIPS 2024 Workshop on Adaptive Foundation Models! adaptive-foundation-models.org We are excited to welcome speakers Matthias Bethge Sander Dieleman Kate Saenko Russ Salakhutdinov Minjoon Seo Bing Liu Tianqi Chen With co-organizers Mengye Ren Naila Murray Renjie Liao Beidi Chen Wei-Chiu Ma

For too long, users have lived under the software lottery tyranny of fused attention implementations. No longer. Introducing FlexAttention, a new PyTorch API allowing for many attention variants to enjoy fused kernels in a few lines of PyTorch. pytorch.org/blog/flexatten… 1/10

Excited to share that I will be joining UCSD CSE as an assistant professor in January 2026! I'll be recruiting PhD students from the 2024 application pool - if you're interested in anything ML Sys/efficiency/etc please reach out & put my name on your application! Until then

Introducing *Transfusion* - a unified approach for training models that can generate both text and images. arxiv.org/pdf/2408.11039 Transfusion combines language modeling (next token prediction) with diffusion to train a single transformer over mixed-modality sequences. This

🤯This study explains my year-long confusion on why #GPT4 leak says OpenAI deployed speculative decoding in their serving last June by Dylan Patel SemiAnalysis because I thought SD is only useful for small batches... Surprisingly speculative decoding can bring more benefits when

Congratulations Jiawei Zhao on an excellent PhD defense! Jiawei has been a pioneer in hardware-efficient training. When he started his PhD, everyone was focusing on inference efficiency, and training runs were small, Jiawei took the bold step to pursue training efficiency. Slides:

#MLSys2025 call for papers is out! The conference will be led by the general chair Matei Zaharia , PC chairs Yingyan (Celine) Lin, and Gauri Joshi. Consider submitting and bringing your latest works in AI and systems—more details at mlsys.org.

We are excited to share our latest work on speculative decoding for high-throughput inference! Before this work, we thought speculative decoding was useless at large batch sizes since the GPUs would go brrrr from processing all the different inputs. Much to our surprise, we

WOW well deserved~ Albert Gu