Audrey Huang Profile
Audrey Huang

@auddery

Followers
129
Following
77
Media
0
Statuses
16

Joined May 2024
Don't wanna be here? Send us removal request.
@auddery
Audrey Huang
8 hours
RT @geneli0: like everyone else i am hopping on the blog post trend.
gene.ttic.edu
A personal website.
0
30
0
@auddery
Audrey Huang
3 days
RT @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 o….
0
2
0
@auddery
Audrey Huang
4 days
RT @nanjiang_cs: missing ICML, and I used this week to write my first technical blog on some recent thoughts on two different roles of simu….
0
19
0
@auddery
Audrey Huang
3 months
RT @Nived_Rajaraman: Announcing the first workshop on Foundations of Post-Training (FoPT) at COLT 2025!. 📝 Soliciting abstracts/posters exp….
0
28
0
@auddery
Audrey Huang
3 months
RT @canondetortugas: RL and post-training play a central role in giving language models advanced reasoning capabilities, but many algorithm….
0
7
0
@auddery
Audrey Huang
3 months
RT @canondetortugas: Is Best-of-N really the best we can do for language model inference?  . New algo & paper: 🚨InferenceTimePessimism🚨. Le….
0
24
0
@auddery
Audrey Huang
3 months
RT @canondetortugas: Akshay presenting InferenceTimePessimism, a new alternative to BoN sampling for scaling test-time compute. From our re….
Tweet card summary image
arxiv.org
Inference-time computation offers a powerful axis for scaling the performance of language models. However, naively increasing computation in techniques like Best-of-N sampling can lead to...
0
9
0
@auddery
Audrey Huang
3 months
RT @liyzhen2: #AISTATS2025 day 3 keynote by Akshay Krishnamurthy about how to do theory research on inference time compute 👍.@aistats_conf….
0
9
0
@auddery
Audrey Huang
5 months
RT @canondetortugas: Our work on language model self-improvement will appear as an Oral at ICLR! See you in Singapore!. .
0
12
0
@auddery
Audrey Huang
7 months
RT @canondetortugas: Given a high-quality verifier, language model accuracy can be improved by scaling inference-time compute (e.g., w/ rep….
0
47
0
@auddery
Audrey Huang
1 year
RT @yus167: New work on understanding preference fine-tuning/RLHF -- we analyze online and offline preference fine-tuning methods via the t….
0
14
0