Azalia Mirhoseini
@Azaliamirh
Followers
14K
Following
2K
Media
35
Statuses
350
Asst. Prof. of CS at Stanford, Google DeepMind. Prev: Anthropic, Google Brain. Co-Creator of MoEs, AlphaChip, Test Time Scaling Laws.
Stanford, CA
Joined May 2013
Excited to release SWiRL: A synthetic data generation and multi-step RL approach for reasoning and tool use!. With SWiRL, the model’s capability generalizes to new tasks and tools. For example, a model trained to use a retrieval tool to solve multi-hop knowledge-intensive
5
74
395
So happy to see the strong interest in KernelBench, our AI for AI acceleration benchmark! . The team has released some updates today:.
KernelBench v0.1 is out, featuring:.- A guideline on analyzing the validity of results and ruling out physically impossible performance claims. - Support for randomized testing beyond normal distributions. - Fixed problem sizes and improved numerics
1
6
54
RT @lmthang: Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the Inte….
0
229
0
RT @quocleix: Excited to share that a scaled up version of Gemini DeepThink achieves gold-medal standard at the International Mathematical….
deepmind.google
Our advanced model officially achieved a gold-medal level performance on problems from the International Mathematical Olympiad (IMO), the world’s most prestigious competition for young...
0
50
0
RT @RylanSchaeffer: If you want to learn about the power (laws) of large language monkeys (and get a free banana 🍌), come to our poster at….
0
6
0
RT @simonguozirui: At #ICML2025 in Vancouver 🇨🇦 this week, presenting some work from my first year at Stanford! Come find me at posters or….
0
14
0
Looking forward to attending ICML!. Here are some works on memory/long context, verification, kernel design, multi-model AI systems, and theoretical understanding of test-time scaling from my awesome students and collaborators!
3
17
86
RT @chrmanning: I’ve joined @aixventureshq as a General Partner, working on investing in deep AI startups. Looking forward to working with….
wsj.com
Christopher Manning, one of the most cited researchers in the field of natural language processing and a former director of the Stanford AI Lab, has taken a leave of absence from Stanford University...
0
34
0
RT @CaiaCostello: So excited to speak tomorrow about Think Prune Train at LAD'25 session on Reasoning and Self Improvement!. .
iclad.ai
0
1
0
RT @oscrhong: Interesting tidbit from prof @chrmanning: The first mention of “Large Language Model” comes from a 1998 NLP workshop Taiwan!….
0
6
0
RT @iScienceLuvr: Shrinking the Generation-Verification Gap with Weak Verifiers. "we introduce Weaver, a framework for designing a strong v….
0
27
0
RT @ajratner: Very exciting work on using weak supervision for RL- closing the “generation-verification gap”!! Once again- principled appr….
0
7
0
See @JonSaadFalcon's post for more details: Paper: .Blog: Datasets and Models:
huggingface.co
How can we close the generation-verification gap when LLMs produce correct answers but fail to select them? .🧵 Introducing Weaver: a framework that combines multiple weak verifiers (reward models + LM judges) to achieve o3-mini-level accuracy with much cheaper non-reasoning
0
3
13
Introducing Weaver, a test time scaling method for verification! . Weaver shrinks the generation-verification gap through a low-overhead weak-to-strong optimization of a mixture of verifiers (e.g., LM judges and reward models). The Weavered mixture can be distilled into a tiny
3
50
225
Congratulations, @CaiaCostello.and Adrian!.
So proud of @CaiaCostello who graduated with her CS masters from @stanfordeng 🎓 today! Lucky to have helped her with the TPT project along with @annadgoldie and @Azaliamirh. This is from her presenting the TPT poster at ICLR 🇸🇬workshop!
2
1
16
Congratulations, Dr. Goldie! @annadgoldie.
Huge congratulations to @annadgoldie on receiving her @Stanford PhD today! It’s been a great journey!
1
1
61
RT @soumithchintala: This is a proper Vibe-coding setup for GPU programmers, and can result in getting surprisingly far!. I honestly think….
0
36
0
Go, @realSharonZhou and team! Congrats to @LisaSu and AMD on such an amazing addition!.
Welcome aboard @realSharonZhou! So happy to have you and the team joining us as we bring @AIatAMD to the world!!!.
1
0
18
RT @teortaxesTex: I like this idea very much and have long advocated for something like this. Synthetically enriched «KV prefix» is a natur….
0
17
0