1. X
  2. Yuchen Zeng
Log inSign up
Yuchen Zeng
205 posts
Image
user avatar
Yuchen Zeng
@yzeng58
Researcher @MSFTResearch, AI Frontiers Lab | Reasoning, Agent | Previously @Meta @MSFT_GSL @MITIBMLab @WisconsinCS
Redmond, WA
yzeng58.github.io
Joined March 2017
765
Following
1,242
Followers
RepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Yuchen Zeng
    @yzeng58
    Jun 24
    💻Tired of running so many slow, expensive benchmark evals across every checkpoint? Try ✨BenchPress✨ at microsoft.github.io/benchpress/: provide a few benchmark scores, then get predictions for the remaining ~100 benchmarks, with trust probabilities and calibrated 90% prediction
    Image
    00:00
    user avatar
    Dimitris Papailiopoulos
    @DimitrisPapail
    Feb 25
    Article cover image
    Article
    You Don't Need to Run Every Eval
    I used Claude Code to build BenchPress a $0 benchmark prediction system, Codex to audit it for bugs, and Claude Sonnet to try to beat it for $1. Here's what I found: LLM evals are so low-rank (in fact...
    30K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Feb 17, 2024
    In-context learning (ICL) excels with LLMs, but what about MLLMs? 📜 Our paper: • Highlights an important problem: Text-to-Image ICL (T2I-ICL) • Introduces 🔥CoBSAT🔥, the first T2I-ICL dataset • Benchmarks MLLMs, explores challenges & enhances T2I-ICL performance 1/n 🧵
    Image
    Image
    22K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Oct 15, 2024
    📢 Excited to share our latest research: "Parameter-Efficient Fine-Tuning of State Space Models" arxiv.org/abs/2410.09016 Existing PEFT works well for Transformers, but what about State Space Models like S4 and Mamba? Our study combines theory and empirics to show: not quite!
    user avatar
    Kangwook Lee
    @Kangwook_Lee
    Oct 15, 2024
    🚀 Excited to share our latest research: "Parameter-Efficient Fine-Tuning of SSMs" Summary: 🧵
    Image
    19K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Oct 27, 2023
    We delve into the theory behind LoRA's remarkable empirical performance, showing that LoRA can adapt any model to exactly approximate a target model given a small rank! 🎯 "The Expressive Power of Low-Rank Adaptation" by me and my advisor @Kangwook_Lee arxiv.org/abs/2310.17513
    user avatar
    Kangwook Lee
    @Kangwook_Lee
    Oct 27, 2023
    🧵 1/8 📣 Excited to share our new paper led by my student @yzeng58! "The Expressive Power of Low-Rank Adaptation" #LoRA #finetuning #LLM #diffusion arxiv.org/abs/2310.17513
    Image
    21K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Nov 11, 2024
    🎉 Milestone: Our LIFT paper has hit 100+ citations! We introduced a simple method to adapt LLMs to new domains, and researchers are now achieving success with it across predictive chemistry, metamaterial physics & more! Check our work at
    uw-madison-lee-lab.github.io
    LIFT: Language-Interfaced Fine-Tuning
    A framework that enables fine-tuning language models for non-language tasks without architectural changes, demonstrating competitive performance across classification and regression tasks.
    21K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Dec 15, 2023
    Exciting day at #NeurIPS! Presenting two papers today: 1. The Expressive Power of Low-Rank Adaptation, 3:00-4:00 p.m., OPT workshop, 📍 Hall D. 2. Outlier-Robust Group Inference via Gradient Space Clustering, 10:30 a.m.-12:00 p.m., DistShift workshop, 📍 Room R06-R09 (Level 2).
    Image
    Image
    11K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Jun 14, 2022
    Are you tired of changing model architectures and coding for different machine learning tasks? 🙌 Let the pretrained language model do the things for you by asking it: when x1 = 1 and x2 = 2, what is y? With appropriate fine-tuning, this works well for various non-language tasks!
    user avatar
    Kangwook Lee
    @Kangwook_Lee
    Jun 14, 2022
    😎! Finetuning a pretrained lang model (e.g., GPT3) has become a popular approach to solve many text-based tasks. This paradigm is making ML very accessible as all you need to prepare is text data for finetuning. Does it also work for non-text tasks? Surprisingly, yes!!! (1/8)
    Image
  • user avatar
    Yuchen Zeng
    @yzeng58
    May 1, 2023
    [#ICLR Today 11:30 am at MH1-2-3-4 #157] Are rejected groups treated fairly under current fairness notions? We study this issue and solve it with our new fairness notion, Equal Improvability, which takes long-term impact into consideration!
    user avatar
    Kangwook Lee
    @Kangwook_Lee
    May 1, 2023
    1/5 Introducing Equal Improvability (EI), our new effort-based fairness notion for ML classifiers. With many existing definitions, why another? Current notions have key limitations! If you're at #ICLR2023, join today’s poster session @ 11:30 AM!
    Image
    2.4K
  • user avatar
    Yuchen Zeng
    @yzeng58
    Oct 1, 2021
    Image
  • user avatar
    Yuchen Zeng
    @yzeng58
    Oct 27, 2023
    Replying to @yzeng58 and @Kangwook_Lee
    I am actively seeking summer internships for 2024, specifically in the areas of Large Language Models (LLMs), model adaptation, and evaluation. If you have any related openings, please feel free to direct message me. 😁
    791
  • user avatar
    Yuchen Zeng
    @yzeng58
    Nov 11, 2024
    Replying to @yzeng58
    🎯 Currently on the job market - open to industry & postdoc positions in LLMs & MLLMs! If interested, please DM me directly or drop me an email [email protected]!
    647
  • user avatar
    Yuchen Zeng
    @yzeng58
    Jun 27, 2024
    Replying to @siyan_zhao
    Congratulations on your excellent work! :) We also explored a similar problem in our 2022 NeurIPS publication, which you can find here: arxiv.org/abs/2206.06565. Our study compares the decision boundaries of "finetuned" LLM with those of traditional models.
    Image
    718
  • user avatar
    Yuchen Zeng
    @yzeng58
    Feb 17, 2024
    Replying to @yzeng58
    2/n 🧵 Why T2I-ICL matters? Multimodal ICL expands ICL's capabilities to MLLMs. T2I-ICL, a novel aspect of Multimodal ICL, diverges from the commonly explored image-to-text direction, opening doors to innovative applications. See the image below for examples.
    Image
    641
  • user avatar
    Yuchen Zeng
    @yzeng58
    Nov 11, 2024
    Replying to @yzeng58
    Back in 2022, our paper already demonstrated LLM's capability in regression, tabular classification, image classification, and even image generation. The core insight? Simply represent your data as sentences! This simple approach opened doors for applications across many fields.
    Image
    655
Advertisement
Advertisement