Azalia Mirhoseini Profile
Azalia Mirhoseini

@Azaliamirh

Followers
15K
Following
2K
Media
37
Statuses
382

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
Don't wanna be here? Send us removal request.
@Azaliamirh
Azalia Mirhoseini
2 days
Introducing intelligence per watt, and predicting a distribution shift from cloud to edge inference!
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
3
9
66
@CMEGroup
CME Group
2 months
Drive your trading strategy forward with CME Group.
22
93
389
@Avanika15
Avanika Narayan
2 days
compute efficiency defined the transition from mainframes to pcs intelligence efficiency (intelligence per watt) will define the transition from cloud ai to local ai excited to release new work studying local ai efficiency with the 🐐's @jonsaadfalcon and @hazyresearch we find
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
3
4
17
@_akhaliq
AK
2 days
Intelligence per Watt Measuring Intelligence Efficiency of Local AI
5
9
67
@Azaliamirh
Azalia Mirhoseini
2 days
Work led by @JonSaadFalcon and @Avanika15, with the amazing John Hennessy, @HazyResearch, and team!
1
0
5
@Jaxxonjewelry
JAXXON
16 days
Style built for the spotlight. Crafted for performance. Blake Snell wears JAXXON.
0
11
117
@Azaliamirh
Azalia Mirhoseini
2 days
A shift from cloud to edge? We took a closer look at “Local LMs” (≤20B active parameters) and found that they are: - Surprisingly capable, with 3.1× improvement since 2023 - Increasingly efficient, with 5.3x improvement since 2023 This suggests a shift from mainframe inference
4
17
76
@stanfordnlp
Stanford NLP Group
20 days
At the retreat, we’re hearing about the exciting work of a few of our current students: @JulieKallini, @JonSaadFalcon, @ShichengGLiu, @kothasuhas, …
2
10
74
@anneouyang
Anne Ouyang
21 days
Really awesome writeup by my lab mate Simon @simonguozirui on AI-generated GPU kernels! We've believe in this problem since I first met my advisor Azalia @Azaliamirh as I was applying to Stanford. Grateful to be working on such a cool problem, amazing to see how far the field
@simonguozirui
Simon Guo
21 days
Wrote a 1-year retrospective with @a1zhang on KernelBench and the journey toward automated GPU/CUDA kernel generations! Since my labmates (@anneouyang, @simran_s_arora, @_williamhu) and I first started working towards this vision around last year’s @GPU_mode hackathon, we have
2
9
142
@jaseweston
Jason Weston
1 month
Was super fun to organize this workshop!! Thanks everyone: speakers, panelists, audience. https://t.co/ccZzIXFgTY
5
11
140
@metafide_ai
Metafide AI
3 days
When Bitcoin moves 2% and you start planning early retirement.
63
62
117
@achowdhery
Aakanksha Chowdhery
1 month
I've spent years pushing the boundaries of pretraining—first as lead author on PaLM, then as a lead contributor on Gemini pre-training. Now I'm at Reflection, building open-weight agentic models at the frontier from the ground up. Today we're announcing our Series B to
Tweet card summary image
reflection.ai
Reflection is a research and product company with the mission to build open superintelligence. We are hiring across all roles!
@reflection_ai
Reflection AI
1 month
Today we're sharing the next phase of Reflection. We're building frontier open intelligence accessible to all. We've assembled an extraordinary AI team, built a frontier LLM training stack, and raised $2 billion. Why Open Intelligence Matters Technological and scientific
49
28
588
@SakanaAILabs
Sakana AI
2 months
Cool to see works like AB-MCTS, The AI Scientist and the Darwin Gödel Machine being included in the new “Self-improving AI Agents” course at Stanford! https://t.co/gwgnNe47Hp
5
68
463
@Azaliamirh
Azalia Mirhoseini
2 months
Very excited to teach CS329A: Self-Improving AI Agents, with @achowdhery for the second time in 2025! Course website:
@kaien_yang
Kaien Yang
2 months
Fully packed first class! Excited to TA Stanford CS329A, Self-Improving AI Agents, with @achowdhery @Azaliamirh @boson2photon. Here's to an amazing quarter!
22
123
1K
@Azaliamirh
Azalia Mirhoseini
2 months
Congrats to my PhD student @anneouyang on @Standard_Kernel! Super excited to see the amazing things she will build!!
@anneouyang
Anne Ouyang
2 months
Excited to share what friends and I have been working on at @Standard_Kernel We've raised from General Catalyst (@generalcatalyst), Felicis (@felicis), and a group of exceptional angels. We have some great H100 BF16 kernels in pure CUDA+PTX, featuring: - Matmul 102%-105% perf
4
16
181
@crossriverbank
Cross River Bank
9 days
Who says crypto has to be complicated? Meet our cutest educators yet: Cross River kids! They're helping us explore crypto concepts with clarity, curiosity, and a lot of charm! Watch the video to learn from the experts!
13
16
60
@Azaliamirh
Azalia Mirhoseini
3 months
More details in Jacky's post: https://t.co/BbL3AuergA
@jackyk02
Jacky Kwok
4 months
✨ Test-Time Scaling for Robotics ✨ Excited to release 🤖 RoboMonkey, which characterizes test-time scaling laws for Vision-Language-Action (VLA) models and introduces a framework that significantly improves the generalization and robustness of VLAs! 🧵(1 / N) 🌐 Website:
0
0
11
@Azaliamirh
Azalia Mirhoseini
3 months
Happy to share RoboMonkey, a framework for synthetic data generation + scaling test time compute for VLAs: Turns out generation (via repeated sampling) and verification (via training a verifier on synthetic data) works well for robotics too! Training the verifier: we sample N
5
32
166
@Azaliamirh
Azalia Mirhoseini
4 months
So happy to see the strong interest in KernelBench, our AI for AI acceleration benchmark! The team has released some updates today:
@anneouyang
Anne Ouyang
4 months
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
8
56
@lmthang
Thang Luong
4 months
Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the International Mathematical Olympiad! 🏆, solving five out of six problems perfectly, as verified by the IMO organizers! It’s been a wild run to lead this
@lmthang
Thang Luong
1 year
Super thrilled to share that our AI has has now reached silver medalist level in Math at #imo2024 (1 point away from 🥇)! Since Jan, we now not only have a much stronger version of #AlphaGeometry, but also an entirely new system called #AlphaProof, capable of solving many more
79
231
2K
@quocleix
Quoc Le
4 months
Excited to share that a scaled up version of Gemini DeepThink achieves gold-medal standard at the International Mathematical Olympiad. This result is official, and certified by the IMO organizers. Watch out this space, more to come soon! https://t.co/4KynCY6M6C
Tweet card summary image
deepmind.google
The International Mathematical Olympiad (“IMO”) is the world’s most prestigious competition for young mathematicians, and has been held annually since 1959. Each country taking part is represented by…
9
54
708
@nirvana_fi
Nirvana 📿
10 days
On-chain DATs are coming to @Solana. Imagine if they could never fall below NAV. That’s Samsara. 📿 Which asset should go first? $BONK, $PENGU, $PUMP or something new? Comment below ↓
14
8
55
@RylanSchaeffer
Rylan Schaeffer
4 months
If you want to learn about the power (laws) of large language monkeys (and get a free banana 🍌), come to our poster at #ICML2025 !!
1
6
68
@willccbb
will brown
4 months
cant stop thinking about this one insanely elegant, seems insanely powerful
26
55
846