Yuning Chai

Head of AI Research @Cruise, Ex-@Waymo, Ex-@Google, PhD @Oxford_VGG @UniofOxford

[Mu Cai @MuCai7]

(1/N ) Can a large multimodal model not only understand bboxes, but also understand arbitrary visual prompts (scribble, arrow, etc) without explicit region embedding? Yes! Our latest work ViP-LLaVA https://t.co/kZ0xGjHEOc shows an extremely simple but effective approach.

[Yuning Chai @yuning_chai]

At CVPR this week. Excited to present our research work at Cruise at the E2E AD workshop (https://t.co/AyUC7v4NzH) on Sunday and the SAIAD workshop (https://t.co/qQGzliRScV) on Monday. See you there!

[Yuning Chai @yuning_chai]

We are open for business for 2023 interns! Our team works on projects across the self-driving stack, from perception, prediction, planning to simulation and testing. If you are interested, please reach out to me, or apply here: https://t.co/WFfjcHUwVx

[Samuel "curry-howard fanboi" Ainsworth @SamuelAinsworth]

📜🚨📜🚨
NN loss landscapes are full of permutation symmetries, ie. swap any 2 units in a hidden layer. What does this mean for SGD? Is this practically useful?

For the past 5 yrs these Qs have fascinated me. Today, I am ready to announce "Git Re-Basin"!

https://t.co/mRu5k3ONUm

[Rowan McAllister @rowantmc]

Wanna switch from academia to industry but unsure how? Here's a guide!

https://t.co/oeXlWAZap5

Thanks to Greg Kahn, Kate Rakelly, @iamborisi, Rebekah Baratho, @ashwinb96, Jessica Yin, @nick_rhinehart, @thejesscat, @RaresAmbrus

[Yuning Chai @yuning_chai]

I was privileged to represent #cruise at the self-driving workshop at #cvpr2022, where I highlighted some of our long-term investments (uncertainty, radar, RL, etc.) and discussed the challenges to deploy the AV. Check out the newly released recording: https://t.co/OZMrC4Q9o3

[Patrick Wenzel @PatrickWenzelML]

An incredible line-up of confirmed speakers:
Abhinav Valada
@AjdDavison
@HLategahn
Philipp Krähenbühl
@yuning_chai

💡 More information: https://t.co/so1zD8mkod

[Yuning Chai @yuning_chai]

@jon_barron Now how many of the 18% "no"s just recently had covid before cvpr? My hypothesis is that the infection rate is a lot higher than 50% among the uninfected. Definitely still worth it tho!

[Yuning Chai @yuning_chai]

Had a full in-person audience + hundreds more on zoom listening to my talk about #Cruise at the WAD workshop at #CVPR22. Recording to follow soon! #SelfDrivingCars

[Yuning Chai @yuning_chai]

Best party in town at barcaria tonight! #cruise #CVPR22

[Yuning Chai @yuning_chai]

@giffmana Don't worry, some of the rooms have had similar issues. Also, Jitendra improvisation was very enjoyable!!

[Yuning Chai @yuning_chai]

Interested in our ongoing effort in deploying driverless vehicle in SF and beyond and happen to be in New Orleans by Chance? Come join my talk at https://t.co/2vCNZiMUnu on Monday:

⏰: 415pm
🛖: Great Hall C

#cruise #CVPR2022 #SelfDrivingCars

[Yuning Chai @yuning_chai]

@giffmana Dude, I think we randomly encounter each other at every past conference anyway :) see u there!

[Yuning Chai @yuning_chai]

Excited to be at the first "real" conference in 2.5 years! Hit me up if you are in New Orleans the coming week! #CVPR22

[Yuning Chai @yuning_chai]

Excited to be in Phila and have to opportunity to present alongside so many robotics visionaries at the Scaling Robot Learning
workshop (https://t.co/BtnQAL1aJB) at ICRA'22 tomorrow! #ICRA2022 #selfDrivingCar #cruise

[Yuning Chai @yuning_chai]

@ChrSzegedy oh lol. I need to follow Twitter more regularly :)

[Yuning Chai @yuning_chai]

@jon_barron Curious which pronunciation __is__ acceptable for the folks answered with no?

[Yuning Chai @yuning_chai]

@TYLERZHU3 You on the torch train now? :)

[Yuning Chai @yuning_chai]

Finally done with the recordings. They are now on YT: https://t.co/tkfv2OFSv0

[Yuning Chai @yuning_chai]

We'll be co-hosting this year's Workshop on Autonomous Driving at CVPR'21 tomorrow (Sunday, 6/20): https://t.co/tTAhohVaR5. We have a star-studded line-up of invited speakers! Event will be streamed on YT: https://t.co/z30Ja5n5kd

[Xinchen Yan @skywalkeryxc]

Our work on Learning Animatable 3D Human Shape and Skeleton in a Single Neural Network.