Skip to yearly menu bar Skip to main content


Timezone: US/Pacific

Registration Desk: Registration Check-in Desk Mon 13 May 07:00 a.m.  


Opening Remarks Mon 13 May 09:00 a.m.  


Invited Talk: Kurt Keutzer

GenAI Efficiency is About More than Models

Kurt Keutzer

 

Kurt is Professor of the Graduate School in the Berkeley AI Research (BAIR) Lab of the Department of Electrical Engineering and Computer Science at University of California, Berkeley. After a distinguished career in Electronic Design Automation where he won many Best Paper awards, as well as a Most Influential Paper of the Decade award, Kurt turned his attention to efficient Machine Learning, and, later, efficient Deep Learning. Kurt is probably best known for his “Squeeze” family of Neural Nets that helped to pioneer the use of Deep Learning at the edge, but he has also collaborated to scale the training of Neural Nets to 1000’s of processors. Kurt’s research is currently moving beyond single-model optimization to efficiently harnessing the power of sophisticated systems of LLMs. He is a Life Fellow of the IEEE.



Talk: Azalia Mirhoseini

Scaling Intelligence

Azalia Mirhoseini

 

I am an Assistant Professor in the Computer Science Department at Stanford University. My research interest is in developing capable, reliable, and efficient AI systems for solving high-impact, real-world problems. My work includes generalized learning-based methods for decision-making problems in systems and chip design, self-improving AI models through interactions with the world, and scalable deep learning optimization. I also spend time at Google DeepMind and prior to Stanford, I spent several years in industry AI labs, including Anthropic and Google Brain. At Anthropic, I worked on advancing the capabilities and reliability of large language models. At Google Brain, I co-founded/led the ML for Systems team, with a focus on automating and optimizing computer systems and chip design. I received my BSc degree in Electrical Engineering from Sharif University of Technology and my PhD in Electrical and Computer Engineering from Rice University. My work has been recognized through the MIT Technology Review’s 35 Under 35 Award, the Best ECE Thesis Award at Rice University, publications in flagship venues such as Nature, and coverage by various media outlets, including MIT Technology Review, IEEE Spectrum, The Verge, The Times, ZDNet, VentureBeat, and WIRED.


















Workshop: Sponsor Lightning Talks Mon 13 May 02:00 p.m.  

Slides for all talks are linked above.

Short overview talks from MLSys sponsors.


Round Table Discussion: Round Table Mon 13 May 03:30 p.m.  

Theme A: career development Theme B: future research of MLSys


Discussion Panel Mon 13 May 04:15 p.m.  

Beidi Chen · Kurt Keutzer · Zhihao Jia · Haifeng Jin · Hui Guan · Tri Dao

Session: Student Poster Session Mon 13 May 05:00 p.m.