Log inSign up
user avatar
Tim Xiao
@TimZXiao
PhD student in Machine Learning @ University of Tübingen · IMPRS-IS scholar
timx.me
Joined June 2012
328
Following
283
Followers
RepliesMedia
  • Pinned
    user avatar
    Tim Xiao
    @TimZXiao
    Jun 13, 2025
    ✨ New paper: Flipping Against All Odds We found that large language models (LLMs) can describe probabilities—but fail to sample from them faithfully. Yes, even flipping a fair coin is hard. 🪙 🧵 Here’s what we learned—and how we fixed it. 🔗arxiv.org/abs/2506.09998 1/
    Image
  • user avatar
    Tim Xiao
    @TimZXiao
    May 28
    Checkout our new project! Being able to post train the largest opensource LLMs on a single node is such a cool achievement!
    user avatar
    Weiyang Liu
    @Besteuler
    May 28
    🚀 Meet Orbit: OFT-based RL infrastructure for stable, efficient post-training of trillion-parameter LLMs. Orbit can train 1T+ LLMs (e.g. Kimi-2.6, DeepSeek-V4-Pro) on a single GPU node (8xB200) with extremely small train-rollout gap! Code: github.com/Sphere-AI-Lab/… Blog:
    Image
    GIF
  • user avatar
    Tim Xiao
    @TimZXiao
    Apr 10
    Nice work! Whether an LLM can generate faithful sample is an important topic for the agentic era. Our work verbalized rejection sampling also studied this problem! arxiv.org/abs/2506.09998
    user avatar
    Petar Veličković
    @PetarV_93
    Apr 10
    can llms reliably roll the dice? 🎲 we shed new light on stochasticity limitations of llms, discussing some ways in which things can improve: tools, prngs, and 'just giving a random number to the model™' great work from @gu_xiangming while being a student researcher with us 🚀
    Image

  • See @TimZXiao's full profile

    Sign up
    Log in