Log inSign up
user avatar
Ethan Chern
@ethanchern
PhD student @sjtu1896
ethanc111.github.io
Joined July 2023
324
Following
189
Followers
RepliesMedia
  • Pinned
    user avatar
    Ethan Chern
    @ethanchern
    Dec 30, 2025
    "Failure is just iteration. No explosion, no innovation. Keep going."🚀 You vent to @elonmusk—he looks you in the eye and replies instantly, like a video call. Introducing LiveTalk: real-time video gen system on a GPU that sees you, reads emotion, and responds in real time.🧵👇
    Image
    00:00
  • user avatar
    Ethan Chern
    @ethanchern
    Jul 8, 2025
    FacTool has been accepted to COLM 2025 - two years after its arXiv debut! While the landscape of LLMs has changed a lot since then, tool-augmented LLMs and RAG are still among the most effective and practical approaches for detecting / mitigating hallucinations (ref:
  • user avatar
    Ethan Chern
    @ethanchern
    May 29, 2025
    We present Thinking with Generated Images, demonstrating how a single unified LMM can be trained to perform vision generation tasks using both textual and visual intermediate steps, along with critique and refinement capabilities. We believe that spontaneous multimodal thinking
    user avatar
    Pengfei Liu
    @stefan_fee
    May 29, 2025
    What if AI could mentally sketch its thoughts, just like you? The missing piece of AI multimodal reasoning is here! What if AI could daydream in images? Closing the imagination gap between humans and AI! Introducing Thinking with Generated Images — a new paradigm where large
    Image
  • user avatar
    Ethan Chern
    @ethanchern
    Sep 27, 2024
    Really nice work! ProX is the pioneering study on the scaling of data quality. ProX introduces a new scaling paradigm, and I look forward to future work that discusses the new scaling law — how training compute should be allocated not only to model size and data size but also to
    user avatar
    Fan Zhou
    @FaZhou_998
    Sep 26, 2024
    🚀 Still relying on human-crafted rules to improve pretraining data? Time to try Programming Every Example(ProX)! Our latest efforts use LMs to refine data with unprecedented accuracy, and brings up to 20x faster training in general and math domain! 👇 Curious about the details?
    Image
    00:00