Jiatao Gu (@thoma_gu) 's Twitter Profile
Jiatao Gu

@thoma_gu

ML Researcher at @Apple (MLR) and Incoming Assistant Prof @CIS_Penn | exFAIRer | PhD @HKUniversity | Research on Generative AI for multimodal. また日本語もできます。

ID: 910633147

linkhttp://jiataogu.me calendar_today28-10-2012 16:22:07

485 Tweet

4,4K Followers

1,1K Following

Jiatao Gu (@thoma_gu) 's Twitter Profile Photo

Feel free to drop by our talks at: June 11 Morning (202 B): vision-x-nyu.github.io/scalable-visio… June 11 Afternoon (Grand A2): generative-vision.github.io/workshop-CVPR-… June 12 Afternoon (103 A): vgm-cvpr.github.io

Jiatao Gu (@thoma_gu) 's Twitter Profile Photo

Congrats Ricky T. Q. Chen to the nice work! This reminds me of our earlier work Levenshtein Transformers (x.com/thoma_gu/statu…) at FAIR! We learned non-autoregressive insertion-deletion network for machine translation. Good memories before the LLM era!

Jiatao Gu (@thoma_gu) 's Twitter Profile Photo

Please drop by and check our highlight poster tomorrow at #CVPR2025! ExHall D Poster #60 Sun 15 Jun 10:30 a.m. CDT — 12:30 p.m. CDT Great work by our Apple intern Qihang Zhang and look forward to more exploration on explicit 3D generation! zqh0253.github.io/wvd/

Lingjie Liu (@lingjieliu1) 's Twitter Profile Photo

Come visit our posters today and chat with us! 🕥 10:30–12:30 – Poster #153 🔹 Ego4D: Egocentric Human Motion Capture & Understanding from Multi-Modal Input 🔗 jianwang-mpi.github.io/ego4o/ 🕓 16:00–18:00 – Poster #37 🔹 Vid2Sim: Generalizable, Video-based Reconstruction of

Come visit our posters today and chat with us!

🕥 10:30–12:30 – Poster #153
🔹 Ego4D: Egocentric Human Motion Capture & Understanding from Multi-Modal Input
🔗 jianwang-mpi.github.io/ego4o/

🕓 16:00–18:00 – Poster #37
🔹 Vid2Sim: Generalizable, Video-based Reconstruction of
Chuang Gan (@gan_chuang) 's Twitter Profile Photo

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or

Lingjie Liu (@lingjieliu1) 's Twitter Profile Photo

I like our Vid2Sim for two main reasons: 1. The inverse physics problem can be efficiently tackled through a generalized feed-forward prediction of physical properties + a lightweight optimization accelerated by the proposed Neural Jacobian. 2. Its handle-based 3D representation

Jiatao Gu (@thoma_gu) 's Twitter Profile Photo

Thanks 9to5Mac for summarizing our research on TARFlow/STARFlow! It is an exciting direction of reviving normalizing flow with modern scalable techniques… and more will come!