Audrey Huang

[Audrey Huang @auddery]

@WuChuanIJ 这波量能确实有点东西了

[Audrey Huang @auddery]

@FYweb3 @binancezh 土狗进城找阿迪玩梗了

[Audrey Huang @auddery]

@WanjunXie 这瓜够大，坐等后续

[Dylan Foster 🐢 @canondetortugas]

Don’t miss our workshop on Foundations of Reasoning in Language Models at NeurIPS tomorrow!

Upper Ballroom 33ABC, starting 8:50 AM

Featuring talks by @Azaliamirh, @aviral_kumar2, @natolambert, and @mhahn29 on self-improvement, exploration, Olmo 3, chain-of thought, and more!

[Nathan Lambert @natolambert]

Never too early for neurips hype

[Dylan Foster 🐢 @canondetortugas]

Announcing the first workshop on Foundations of Language Model Reasoning (FoRLM) at NeurIPS 2025!

📝Soliciting abstracts that advance foundational understanding of reasoning in language models, from theoretical analyses to rigorous empirical studies.

📆 Deadline: Sept 3, 2025

[Audrey Huang @auddery]

@YoungseogC @zicokolter @MicrosoftAI Congratulations!!! so happy for you :)

[Youngseog Chung @YoungseogC]

Life update!! 📣🎉

I defended my PhD thesis!

Big thanks to my wonderful advisor Jeff Schneider and thesis committee @zicokolter, Aarti Singh, and Jasper Snoek.

Next up: I'm joining @MicrosoftAI as a Member of Technical Staff - stoked to be back in the Bay Area!! Idemooooo 🔥💪

[Gene Li @geneli0]

like everyone else i am hopping on the blog post trend

https://t.co/t3Rma35FWC

[Jason Lee @jasondeanlee]

I have been waiting 6 weeks for you to come and schedule us for the blind installation. We have spent 20 hours on phone on hold. Never using home depot again. @HomeDepot @RFInstallations

[Nan Jiang @nanjiang_cs]

missing ICML, and I used this week to write my first technical blog on some recent thoughts on two different roles of simulators in RL and the confusions/misconceptions around them. Comments welcome!

https://t.co/EAM3fIzT4g

[Audrey Huang @auddery]

@_zhuyuchen hey yuchen, i couldn't DM you but i'm looking last-minute for housing. if this is still available, perhaps you can message me?

[Nived Rajaraman @Nived_Rajaraman]

Announcing the first workshop on Foundations of Post-Training (FoPT) at COLT 2025!

📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models!
│
🗓️ Deadline: May 19, 2025

[Dylan Foster 🐢 @canondetortugas]

RL and post-training play a central role in giving language models advanced reasoning capabilities, but many algorithmic and scientific questions remain unanswered.

Join us at FoPT @ COLT '25 to explore pressing emerging challenges and opportunities for theory to bring clarity.

[Dylan Foster 🐢 @canondetortugas]

Is Best-of-N really the best we can do for language model inference?  

New algo & paper: 🚨InferenceTimePessimism🚨

Led by the amazing Audrey Huang (@auddery) with Adam Block, Qinghua Liu, Nan Jiang (@nanjiang_cs), and Akshay Krishnamurthy. Appearing at ICML '25.

1/11

[Dylan Foster 🐢 @canondetortugas]

Akshay presenting InferenceTimePessimism, a new alternative to BoN sampling for scaling test-time compute. From our recent paper here: https://t.co/TdX3LmNIvq

[yingzhen @liyzhen2]

#AISTATS2025 day 3 keynote by Akshay Krishnamurthy about how to do theory research on inference time compute 👍
@aistats_conf

[Audrey Huang @auddery]

@WenSun1 congrats :)

[Dylan Foster 🐢 @canondetortugas]

Our work on language model self-improvement will appear as an Oral at ICLR! See you in Singapore!

https://t.co/eE7akC67wK

[Dylan Foster 🐢 @canondetortugas]

Given a high-quality verifier, language model accuracy can be improved by scaling inference-time compute (e.g., w/ repeated sampling). When can we expect similar gains without an external verifier?

New paper: Self-Improvement in Language Models: The Sharpening Mechanism