Dian Chen

Researcher @ToyotaResearch having fun in CV/ML. Previously researcher @UCBerkeley.

[ege ozguroglu @EgeOzguroglu]

At #CVPR2024: we present pix2gestalt, which synthesizes whole objects from occluded ones, enabling zero-shot amodal segmentation, recognition, and 3D reconstruction!

Project Page: https://t.co/mjvjuEdfYM
Code: https://t.co/0i7sEXsg7x
arXiv: https://t.co/LxJfvtwXio

[Sedrick Keh @sedrickkeh2]

📢 Releasing TRI's open-source Mamba-7B trained on 1.2T tokens of RefinedWeb!

Mamba-7B is the largest fully recurrent Mamba model trained and is a state-of-the-art recurrent LLM. 🚀🚀🚀

https://t.co/PmsoRc4SNG

[Yue Wang @yuewang314]

#VCAD @CVPR is successfully concluded! We sincerely thank speakers and audiences for coming and those fruitful discussions of the future of vision-centric and data-driven driving. Here are some pictures we took at the venue: https://t.co/HM1nLfwVng (credits @xinhaoliu16)

[Dian Chen @dian_chen_]

Happening now in west 204!

[Dian Chen @dian_chen_]

In case you are exploring the agenda on June 19th (Monday) for #CVPR2023 , we are organizing the full-day Vision Centric Autonomous Driving Workshop (VCAD)! Come and join us for wonderful talks and challenges! More details here: https://t.co/iFNliqe3z1

[Dian Chen @dian_chen_]

In case you are exploring the agenda on June 19th (Monday) for #CVPR2023 , we are organizing the full-day Vision Centric Autonomous Driving Workshop (VCAD)! Come and join us for wonderful talks and challenges! More details here: https://t.co/iFNliqe3z1

[Volkan Isler @AgriRobot]

I've just found this picture of @GRASPlab Lab in 2001. Good times!

[Dian Chen @dian_chen_]

Come to our poster 30a at Tuesday morning’s 10:00am - 12:30pm session; we'd love to chat with you about how we made SoTA test-time adaptation with self-supervised contrastive learning! #CVPR2022 #UCBerkeley @DequanWang @trevordarrell @SaynaEbrahimi
https://t.co/AoB9J18Tta

[Toyota Research Institute (TRI) @ToyotaResearch]

Inferring depth from cameras can help save lives, increase mobility, reduce costs, and improve manufacturing processes.

In our latest blog, TRI's machine learning team takes it one step further and shows how to bring #monodepth to the real world ⬇️ https://t.co/Wxe4VhQ6N5

[Dian Chen @dian_chen_]

Check out how we are learning the depth with monocular image @ToyotaResearch! https://t.co/dtAs9yT940

[Dian Chen @dian_chen_]

Checkout our work AdaContrast accepted to #CVPR2022 that achieves SoTA performance on test-time adaptation! Code is available. Shout-out to my wonderful collaborators @UCBerkeley: @DequanWang, @trevordarrell and @SaynaEbrahimi!
https://t.co/AoB9J0Ri4A

[Dian Chen @dian_chen_]

Checkout our work AdaContrast accepted to #CVPR2022 that achieves SoTA performance on test-time adaptation! Code is available. Shout-out to my wonderful collaborators @UCBerkeley: @DequanWang, @trevordarrell and @SaynaEbrahimi!
https://t.co/AoB9J0Ri4A