Log inSign up
Song Han
337 posts
Image
user avatar
Song Han
@songhan_mit
Joined March 2019
207
Following
10.1K
Followers
  • user avatar
    Song Han
    @songhan_mit
    Sep 6, 2024
    Teaching a big class this semester: efficientml.ai
    Image
    65K
  • user avatar
    Song Han
    @songhan_mit
    Sep 8, 2022
    Welcome to my new course on TinyML and Efficient Deep Learning, starting tomorrow: efficientml.ai
  • user avatar
    Song Han
    @songhan_mit
    Nov 4, 2023
    EfficientML.ai Lecture 16 - Diffusion Models (MIT 6.5940, Fall 2023) Denoising diffusion models Conditional diffusion Latent diffusion Image editing Model personalization Fast sampling DDIM Progressive distillation Guided distillation youtu.be/nFE1euQ_Wtw
    58K
  • user avatar
    Song Han
    @songhan_mit
    Aug 29, 2022
    We are excited to open source TinyEngine: memory-efficient and high-performance neural network library for microcontrollers.
    Image
    GitHub - mit-han-lab/tinyengine: [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS...
    From github.com
  • user avatar
    Song Han
    @songhan_mit
    Sep 7, 2023
    EfficientML.ai will be offered again this fall, starting tomorrow. I will teach model compression and acceleration techniques for efficient AI computing. Lectures will be streamed via live.efficientml.ai Tue/Thur 3:30-5:00pm EST. Looking forward to see you.
    45K
  • user avatar
    Song Han
    @songhan_mit
    Feb 5, 2024
    It's time to systematically study the fundamental principles of GPU-accelerated AI computing:
    Image
    youtube.com
    EfficientML.ai Course | 2023 Fall | MIT 6.5940
    Large generative models (e.g., large language models, diffusion models) have shown remarkable performances, but their enormous scale demands significant comp...
    28K
  • user avatar
    Song Han
    @songhan_mit
    Nov 22, 2024
    ⚡️ SANA is released: github.com/NVlabs/Sana Demo: nv-sana.mit.edu Highlight: - 20 x smaller & 100x faster than FLUX - Generate 4K image. - Deployable on laptop GPU.
    Image
    00:00
    19K
  • user avatar
    Song Han
    @songhan_mit
    Sep 12, 2023
    EfficientViT is highlighted by MIT home page today: mit.edu. EfficientViT accelerates Segment Anything from 12 images/s to 842 images/s on a GPU. Key idea: light-weighted multi-scale linear attention. Full story: news.mit.edu/2023/ai-model-…
    mit.edu
    The Massachusetts Institute of Technology (MIT)
    The mission of MIT is to advance knowledge and educate students in science, technology and other areas of scholarship that will best serve the nation and the world in the 21st century.
    29K
  • user avatar
    Song Han
    @songhan_mit
    Sep 12, 2024
    Welcome to the live stream of EfficientML.ai lectures, every Tue/Thur 3:35-5pm ET at live.efficientml.ai, today we'll introduce pruning, part 1.
    Image
    22K
  • user avatar
    Song Han
    @songhan_mit
    Feb 4, 2024
    Proud moment of my first PhD student passing his thesis defense, "Efficient Deep Learning Computing: From TinyML to Large Language Model" youtu.be/E7cOyB20HDM. Congrats Ji Lin! @jilin_14
    20K
  • user avatar
    Song Han
    @songhan_mit
    Jun 20, 2024
    The enrollment of my MIT class EfficientML.ai is projected to double again this year. For those who can not enroll at MIT, welcome to take the online version: live.efficientml.ai
    Image
    24K
  • user avatar
    Song Han
    @songhan_mit
    May 15, 2024
    AWQ received best paper award at MLSys. AWQ quantized models have been downloaded more than a million times on HuggingFace.
    Image
    Image
    19K
  • user avatar
    Song Han
    @songhan_mit
    May 3, 2024
    We release VILA-1.5, an efficient visual language model (VLM) that can understand not only images but also videos. VILA-1.5 achieves state-of-the-art accuracy among open source VLMs on the MMMU dataset. CVPR'24 paper: arxiv.org/pdf/2312.07533 Code: github.com/Efficient-Larg…
    user avatar
    NVIDIA AI Developer
    NVIDIA
    @NVIDIAAIDev
    May 3, 2024
    🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. 🤔Read our technical deep dive ➡️ nvda.ws/3QyZQzJ. In the past, vision language models have struggled with in-context
    Image
    33K

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