Postdoc in EECS @MIT | Previous: PhD in CS @Stanford; BS in math @Tsinghua_Uni | ❤️ 3D vision, geometry, and art
Joined February 2020
- Tweets471
- Following424
- Followers3.9K
- Likes1.9K
Congyue Deng retweeted
Meet Pika H3 Flex, debuting today as the #1 open weight model on DesignArena’s t2v board.
It’s built for professional iteration, with exportable audio stems, resolutions up to 4k, and faster-than-realtime generation. It can produce a 15-second clip with soundtrack in as little as 7 seconds.
So, yeah. It’s kind of a flex 💅
Congyue Deng retweeted
We’re sending TPUs to space (yes, really).
After years of research, we’re launching a satellite to evaluate if and how Google Tensor Processing Units (TPUs) hold up in orbit.
The test mission, as part of our latest moonshot — Project Suncatcher — is designed to gather data exploring how we can one day host machine learning infrastructure in space.
ALT White text on a black background with photos of a TPU and a rocket orbiting Earth. The text reads: “Meet Project Suncatcher, our moonshot to test whether we can host AI infrastructure in space.”
ALT An image showing circuit boards, overlaid with text that reads: “We partnered with Planet to send a prototype satellite carrying four TPUs into orbit. We’ll be looking to see how well the TPUs withstand the harsh conditions of space to assess whether we can eventually host machine learning in orbit.”
Great thanks to Shengqi Chen (github.com/Harry-Chen), vidax is now optimized and tested on TPU v7. Splash attention integrated, ~13x throughput in end-to-end generation!
In my spare time, I wrote a TPU library translating a majority of video models from PyTorch to Jax.
💿Source code: github.com/FlyingGiraffe/vid…
📑Tech report: arxiv.org/abs/2609.18077
🧊Quick try with PyPI: pypi.org/project/vidax/
Great thanks to @Google TPU Research Cloud (TRC)!
In my spare time, I wrote a TPU library translating a majority of video models from PyTorch to Jax.
💿Source code: github.com/FlyingGiraffe/vid…
📑Tech report: arxiv.org/abs/2609.18077
🧊Quick try with PyPI: pypi.org/project/vidax/
Great thanks to @Google TPU Research Cloud (TRC)!
Congyue Deng retweeted
Want to join our speakers for dinner at #ECCV2026?
We have a stellar lineup at the Workshop on Geometric Intelligence in Malmö, and are giving away tickets to the exclusive speaker dinner.
Attend the workshop, participate in the sessions, and enter for a chance to win your seat!
Congyue Deng retweeted
🚀 CFP: 1st Workshop on #PhysWorldAI at #NeurIPS2026!
Explore physical geometry, physical properties, multimodal sensing & embodied AI.
🎤 Keynotes: Anandkumar, Snavely, Finn & Freeman.
📍Atlanta, Dec 12/13 | 📅 Due Sept 9
physworld-org.github.io/phys…
Congyue Deng retweeted
Incredibly honored and grateful to receive the ACM SIGGRAPH Significant New Researcher Award! My sincere thanks to SIGGRAPH and the award committee, and to my mentors, students, collaborators, colleagues, and family for all their support along the way. It’s an exciting time for 3D and AI, and I feel fortunate to be part of this community. Thank you, Kostas, for the kind words and continued support!
Congratulations to @LingjieLiu1 for receiving the ACM SIGGRAPH Significant New Researcher Award! We are thrilled and so proud of you!
siggraph.org/awards/signific…
Congyue Deng retweeted
Excited to announce: In 2027 I'll join the UW Allen School (@UWCSE) in Seattle as tenure-track faculty in Computer Science!
My group will advance core geometry processing + 3D AI for visual computing, science, & engineering. I'll be recruiting PhD students in the next cycle!
Congyue Deng retweeted
📢 We are still looking for reviewers!
If you are passionate about graph learning and geometry and would like to contribute to the community, we encourage you to apply!
🖋️ Application form: docs.google.com/forms/d/e/1F…
Don’t forget: top reviewers will receive monetary rewards!
Congyue Deng retweeted
Working on vision for robotics, biology, or chemistry?
Passionate about pushing science forward?
The submission deadline for our #ECCV2026 workshop, Geometric Intelligence, is coming up on July 20!
Don’t forget to submit your work:
geo-int.github.io/
Congyue Deng retweeted
Reiterating a Call for Papers! #ECCV2026 Workshop on X-Reason: Visual Perception and Reasoning in the Interactable World 🤖
We welcome works at intersection of computer vision, spatial reasoning, robotics, autonomous driving, and embodied AI.
🌐Website: xreason-workshop.github.io
🤖 Made with AI
Congyue Deng retweeted
🗓️Submission deadline: Jul 31, 2026
🔗Submit: openreview.net/group?id=thec…
f.com/ECCV/2026/Workshop/X-R…
Big thanks to my amazing co-organizers
@CongyueD, Lena Wild, @milanganai, @HaoranGeng2, @vitorguizilini, @JitendraMalikCV, and Leonidas Guibas
📢 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀: #ECCV2026 Workshop on Geometric Intelligence: From Vision to Scientific Discovery
All researchers in computer vision, machine learning, AI-for-Science, and any related field are welcome to submit their work!
📷 Website: geo-int.github.io
Big thanks to the organizers:
@lennart_bastian
@GaoMaolin
Yizheng Xie
@lily_goli
@_R_Marin_
@tolga_birdal
@taiyasaki
Bill Freeman
@GuibasLeonidas
Daniel Cremers
Congyue Deng retweeted
Inspired by #CVPR2026?
📣 Announcing: Call For Papers on Geometric Intelligence @ ECCV26!
geo-int.github.io/
Submission deadline: 13th of July
👀 Computer vision and AI are increasingly playing a role in scientific discovery. 1/n
Call for Papers! #ECCV2026 Workshop on Visual Perception and Reasoning in the Interactable World
Reasoning is fast becoming a fundamental substrate for embodied systems and physical AI, and it's reshaping perceptual understanding.
🔗Website: xreason-workshop.github.io/
Stacked speaker lineup bridging academia + industry.
Submit. Share. See you in Malmö!
#ECCV2026 #EmbodiedAI #PhysicalAI #Robotics