Correction re the time: my posters on Q# and VGS at @ai4mathworkshop is happening today from 10:50 am to 12:20 pm. Hope to see you there!
x.com/kaiwenw_ai/sta…
Correction re the time: my posters on Q# and VGS at @ai4mathworkshop is happening today from 10:50 am to 12:20 pm. Hope to see you there!
x.com/kaiwenw_ai/sta…
This captures something fundamental we're seeing in AI right now! The shift from just scaling pre-training to scaling test-time compute is huge. Our Q# + VGS work shows how value-based methods can guide models through the vast implicit graphs of reasoning possibilities.
This captures something fundamental we're seeing in AI right now! The shift from just scaling pre-training to scaling test-time compute is huge. Our Q# + VGS work shows how value-based methods can guide models through the vast implicit graphs of reasoning possibilities.
How can small LLMs match or even surpass frontier models like DeepSeek R1 and o3 Mini in math competition (AIME & HMMT) reasoning? Prior work seems to suggest that ideas like PRMs do not really work or scale well for long context reasoning. @kaiwenw_ai will reveal how a novel…
How can small LLMs match or even surpass frontier models like DeepSeek R1 and o3 Mini in math competition (AIME & HMMT) reasoning? Prior work seems to suggest that ideas like PRMs do not really work or scale well for long context reasoning. @kaiwenw_ai will reveal how a novel…
Are world models necessary to achieve human-level agents, or is there a model-free short-cut?
Our new #ICML2025 paper tackles this question from first principles, and finds a surprising answer, agents _are_ world models… 🧵
I've made FANG billions of $ with reinforcement learning, so this episode is a long-time coming :-).
Episode 180: Reinforcement Learning, drops on Monday!
patreon.com/posts/180-lear…
Making inferences robust to distribution shifts and hidden confounders is paramount for decision making under uncertainty.
At the upcoming @NeurIPSConf, I’m excited to present our efficient and sharp algorithm for off-policy evaluation in robust markov decision processes.
Many…
2022: I never wrote a RL paper or worked with a RL researcher. I didn’t think RL was crucial for AGI
Now: I think about RL every day. My code is optimized for RL. The data I create is designed just for RL. I even view life through the lens of RL
Crazy how quickly life changes
89 Followers 648 Followingphd @tamu. prev: swe @stripe, bs @utaustin. i want to mechanistically understand models through the lens of training dynamics. 🇵🇪🏳️🌈
158 Followers 1K FollowingRL PhD @manningcics | CS Masters @UWaterloo | UG @IITKgp | DeepRL and Foundation and World Models for Decision Making Agents
Perv @ml_umd, @ClipUmd, @rlai_lab.
1K Followers 435 FollowingPh.D. student studying AI & decision making at @Mila_Quebec / @McGillU. Currently at @AIatMeta. Previously @GoogleDeepMind, @Google 🧠.
409 Followers 710 FollowingComputational cognitive scientist, postdoctoral fellow @affectivebrain, father of Yuvali & Ariel, and an amateur tennis player 🎾
3K Followers 6K FollowingLLM for code and reasoning. PhD student at Cornell. Previously Student Researcher at @google. Previously intern at @theteamatx.
718 Followers 3K FollowingAI / ML / RL research @Mila_Quebec / @UMontreal, prev. research @Ualberta, @AmiiThinks, @rlai_lab. Open science community lead @Cohere_Labs .
3K Followers 672 FollowingFoundations of AI. I like simple & minimal examples and creative ideas. I also like thinking about going beyond the next token 🧮🧸
Google Research | PhD, CMU
4.4M Followers 3 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202
3K Followers 584 FollowingEconomist at Ramp Economics Lab @tryramp. Writing and analysis of AI, business spend, and the economy at https://t.co/rFk0ZcjkR3. Prev economics lead @square
87K Followers 194 FollowingBuilding beautiful things like Mojo🔥 and MAX @Modular, lifting the world of production AI/ML software into a new phase of innovation. We’re hiring! 🚀🧠
47K Followers 462 FollowingSeparate skill from luck. Maximize the former, minimize the latter, using empirical evidence and thinking from first principles. Sister acct: @yogappygappy.
3K Followers 462 FollowingMaker of the OpenWebText. @Mozilla Rise25 @PyTorch Core Reviewer. PhD Candidate at @Cornell Previously @FacebookAI and @BrownUniversity Graduating May 2025
110 Followers 21 Following2nd AI for Math Workshop @ ICML 2025
West Ballroom C, Vancouver Convention Center
July 18th, 2025 @ Vancouver, Canada (Hybrid)
7K Followers 872 FollowingExperiment tracker purpose-built for foundation model training.
We tweet about #LLM best practices & other cool stuff.
Read our blog at https://t.co/4eACuib1QI
3K Followers 672 FollowingFoundations of AI. I like simple & minimal examples and creative ideas. I also like thinking about going beyond the next token 🧮🧸
Google Research | PhD, CMU
15K Followers 314 FollowingOfficial account of Mohamed bin Zayed University of Artificial Intelligence. Dedicated to research, innovation, and empowering brilliant minds in AI.
5K Followers 691 FollowingResearch Scientist @allen_ai, PhD in NLP 🤖 UofA. Ex @GoogleDeepMind @MSFTResearch @MilaQuebec 🚨🚨 NEW BLOG about LLMs reasoning: https://t.co/Ox0iOaqY7e
8K Followers 6K FollowingPhD student @berkeley_ai; research @cursor_ai; prev @GoogleDeepMind. My friend told me to tweet more. I stare at my computer a lot and make things
15K Followers 168 FollowingResearch scientist @GoogleDeepMind. Past: @Databricks, first hire @MosaicML, @MIT PhD. I post about AI technical progress + sometimes the business side.
5K Followers 669 FollowingIncoming Assistant Prof, Toyota Technical Institute at Chicago @TTIC_Connect
Recruiting PhD students (start 2026) 👀
Will irl - TC0 enthusiast
105K Followers 788 FollowingWriting my own AI story. Recent: NPI, AlphaGo tuning, learn to learn, AlphaCode, Gato, ReST, r-Gemma, Imagen3, Veo, Genie, MAI …
26K Followers 720 FollowingMember of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.