Audrey Huang

21 posts

Audrey Huang

Audrey Huang

@auddery

Katılım Mayıs 2024
82 Takip Edilen176 Takipçiler
Audrey Huang retweetledi
Dylan Foster 🐢
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!
Dylan Foster 🐢 tweet media
English
4
18
84
16.2K
Audrey Huang retweetledi
Dylan Foster 🐢
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
Dylan Foster 🐢 tweet media
English
1
27
162
38.1K
Audrey Huang retweetledi
Youngseog Chung
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 🔥💪
Youngseog Chung tweet media
English
25
7
198
16.8K
Audrey Huang retweetledi
Jason Lee
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
English
4
1
13
3.3K
Audrey Huang retweetledi
Nan Jiang
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! nanjiang.cs.illinois.edu/2025/07/16/sim…
Nan Jiang tweet media
English
4
19
142
11K
Audrey Huang
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?
English
0
0
0
49
Yuchen Zhu
Yuchen Zhu@_zhuyuchen·
Can share more details regarding the situation via pm. Also attach the Airbnb photos.
Yuchen Zhu tweet mediaYuchen Zhu tweet mediaYuchen Zhu tweet mediaYuchen Zhu tweet media
English
1
0
0
244
Yuchen Zhu
Yuchen Zhu@_zhuyuchen·
Long shot but does anyone still need Airbnb for #ICML2025 ? I have booked everything to go but just got diagnosed with an acute disease that now I can't go 😭😭 since not going, the funding body might not reimburse the costs. high appreciate retweeting or contacting re Airbnb 🙏🏻
English
3
6
8
2K
Audrey Huang retweetledi
Nived Rajaraman
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
Nived Rajaraman tweet media
English
1
29
86
33.5K
Audrey Huang retweetledi
Dylan Foster 🐢
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.
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

English
1
6
64
5.8K
Audrey Huang retweetledi
Dylan Foster 🐢
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 🐢 tweet mediaDylan Foster 🐢 tweet media
English
2
22
192
24.1K
Audrey Huang retweetledi
yingzhen
yingzhen@liyzhen2·
#AISTATS2025 day 3 keynote by Akshay Krishnamurthy about how to do theory research on inference time compute 👍 @aistats_conf
yingzhen tweet media
English
1
8
140
15.1K
Audrey Huang retweetledi
Dylan Foster 🐢
Dylan Foster 🐢@canondetortugas·
Our work on language model self-improvement will appear as an Oral at ICLR! See you in Singapore! x.com/canondetortuga…
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

English
1
11
92
7.3K
Audrey Huang retweetledi
Dylan Foster 🐢
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
Dylan Foster 🐢 tweet mediaDylan Foster 🐢 tweet media
English
3
45
250
41.5K
Francesco Faccio
Francesco Faccio@FaccioAI·
I'm thrilled to announce that I'm joining the Discovery team at @GoogleDeepMind in London as a Senior Research Scientist starting this January! It's incredible what the team has achieved in the past decade and I am so looking forward towards more scientific discoveries with AI.
English
17
12
429
34.4K
Audrey Huang retweetledi
Dylan Foster 🐢
Dylan Foster 🐢@canondetortugas·
New preprint: Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning We show that good old fashioned behavior cloning enjoys horizon-independent sample complexity for imitation learning—provided you use the log loss! arxiv.org/abs/2407.15007 Thread below
English
2
28
86
15.9K

Keşfet

@Azaliamirh @aviral_kumar2 @natolambert @mhahn29 @YoungseogC @zicokolter @MicrosoftAI @HomeDepot