Log inSign up
Haotian Tang
109 posts
user avatar
Haotian Tang
@haotiant1998
Ph.D. @MITEECS, B.Eng. @sjtu1896.
Joined September 2021
287
Following
2,124
Followers
  • user avatar
    Haotian Tang
    @haotiant1998
    Dec 31, 2024
    Personal update: I am excited to share that I will join @GoogleDeepMind next week after defending my PhD thesis @MITEECS earlier last month. I will be working on generative models that simulate the physical world. Looking forward to the new journey ahead in 2025!
    Image
    126K
  • user avatar
    Haotian Tang
    @haotiant1998
    Oct 15, 2024
    🚀 We're thrilled to introduce HART, an efficient AR model that generates stunning 1024x1024 images! 🎨✨ HART delivers: ⚡️ 4.5-7.7x higher throughput 🔋 6.9-13.4x less compute 🔥 top-notch FID & CLIP scores, rivaling diffusion models in quality! Code: tinyurl.com/nkvpnhyk
    Image
    24K
  • user avatar
    Haotian Tang
    @haotiant1998
    Jun 6, 2024
    Excited to share my #MLSys 2024 best paper 🏆 presentation on AWQ. AWQ democratizes edge LLM deployment 💻 and has been downloaded over 1 million times on Huggingface 🙌!
    15K
  • user avatar
    Haotian Tang
    @haotiant1998
    Jun 6, 2024
    Replying to @haotiant1998
    AWQ website: hanlab.mit.edu/projects/awq Paper: arxiv.org/abs/2306.00978 Code: github.com/mit-han-lab/ll… Joint work with @jilin_14, @jmtang42, @Shang_mit, Wei-Ming Chen, Wei-Chen Wang, @Guangxuan_Xiao, Xingyu Dang, Prof. @gan_chuang, Prof. @songhan_mit.
    arXiv logo
    arxiv.org
    AWQ: Activation-aware Weight Quantization for LLM Compression and...
    Large language models (LLMs) have transformed numerous AI applications. On-device LLM is becoming increasingly important: running LLMs locally on edge devices can reduce the cloud computing cost...
    1.3K
  • user avatar
    Haotian Tang
    @haotiant1998
    Oct 15, 2024
    Replying to @haotiant1998
    📄 Paper: arxiv.org/abs/2410.10812 🌐 Project: hanlab.mit.edu/projects/hart 🖥 Demo: hart.mit.edu 💻 Code: github.com/mit-han-lab/ha…
    arXiv logo
    arxiv.org
    HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
    We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation...
    1.2K
  • user avatar
    Haotian Tang
    @haotiant1998
    May 8, 2024
    🔥Welcome to try out QServe! TRT-LLM efficiency⚡️ + PyTorch flexibility 😄, your LLM serving turn-key solution 🔑
    user avatar
    Shang Yang
    @Shang_mit
    May 8, 2024
    🔥🎉Thrilled to introduce QServe, our latest breakthrough in efficient LLM serving with W4-A8-KV4 quantization. 🚀⚡1.2-3.5x higher throughput over TensorRT-LLM. 💵 Matches TensorRT-LLM’s A100 throughput with 3x cheaper L40S GPUs. 👐 Code: github.com/mit-han-lab/qs… (1/4)
    Image
    1.1K
  • user avatar
    Haotian Tang
    @haotiant1998
    Oct 15, 2024
    Replying to @haotiant1998
    ✨ How it works: We decompose continuous latents into two parts: 🔹 Discrete tokens for the big picture, modeled by a scalable-resolution AR transformer 🔸 Residual tokens for image details, handled by a lightweight diffusion module (37M parameters, 8 sampling steps)
    Image
    1.4K
  • user avatar
    Haotian Tang
    @haotiant1998
    Jan 22, 2025
    What an achievement! Congrats to the team!
    user avatar
    Demis Hassabis
    @demishassabis
    Jan 21, 2025
    Our latest update to our Gemini 2.0 Flash Thinking model (available here: goo.gle/4jsCqZC) scores 73.3% on AIME (math) & 74.2% on GPQA Diamond (science) benchmarks. Thanks for all your feedback, this represents super fast progress from our first release just this past
    Image
    709
  • user avatar
    Haotian Tang
    @haotiant1998
    Jan 5, 2025
    Replying to @xiuyu_l @GoogleDeepMind and @MITEECS
    Thank you, Xiuyu! See you in the Bay Area!
    61
  • user avatar
    Haotian Tang
    @haotiant1998
    Jan 14, 2025
    Replying to @phillip_lippe @GoogleDeepMind and @m__dehghani
    Excited to work together, Phillip!
    222
  • user avatar
    Haotian Tang
    @haotiant1998
    Jan 5, 2025
    Replying to @daoluc_ @GoogleDeepMind and @MITEECS
    Thank you Luc! It’s my great pleasure to work as the TA for 6.5940!
    67
  • user avatar
    Haotian Tang
    @haotiant1998
    Dec 31, 2024
    Replying to @yule_gan @GoogleDeepMind and @MITEECS
    Thank you, Yulu!
    376
  • user avatar
    Haotian Tang
    @haotiant1998
    Jan 5, 2025
    Replying to @vernons @GoogleDeepMind and @MITEECS
    Thank you Vernon!
    25
  • user avatar
    Haotian Tang
    @haotiant1998
    Mar 25, 2025
    Replying to @TianweiY @MIT and 2 others
    Congrats, Tianwei!
    168

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