Boyi Li (@boyiliee) 's Twitter Profile
Boyi Li

@boyiliee

ID: 1236009554737082369

linkhttp://sites.google.com/site/boyilics/home calendar_today06-03-2020 19:24:18

99 Tweet

1,1K Followers

297 Following

Marco Pavone (@drmapavone) 's Twitter Profile Photo

At NVIDIA GTC, I presented my group's strategy on leveraging foundation models (FMs) to develop next-gen autonomous vehicles. Slides: tinyurl.com/55uhawka Recording: tinyurl.com/3j5kk55a Three pillars: standing up the FMs, using them within an AV program, and AI safety.

Marco Pavone (@drmapavone) 's Twitter Profile Photo

If you are #CVPR2024, consider attending our workshop on "Vision and Language for Autonomous Driving and Robotics" with an amazing lineup of speakers! Details here: vision-language-adr.github.io

Neerja Thakkar (@neerjathakkar) 's Twitter Profile Photo

Human trajectory prediction often assumes consistent behavior trends over time. But human behavior is transient: party-goers act differently at night than when going to work. To address this, our ECCV ’24 paper introduces “latent corridors” for rapid deployment scene adaptation.

Marco Pavone (@drmapavone) 's Twitter Profile Photo

The new Italian Foundation on Artificial Intelligence for Industry (AI4I) is looking for a Director! A unique opportunity to shape the R&D AI agenda in Italy and in Europe (I serve as member of the scientific committee). Apply here: ai4i.it/call-for-direc… Fabio Pammolli #AI

Marco Pavone (@drmapavone) 's Twitter Profile Photo

Video captioning is nowadays a critical tool to fuel data flywheels for AV and robot development. We have just released Wolf: a novel video captioning framework achieving SOTA in a number of settings: Paper: arxiv.org/pdf/2407.18908 Related challenge: wolfv0.github.io/leaderboard.ht…

Marktechpost AI Research News ⚡ (@marktechpost) 's Twitter Profile Photo

Wolf: A Mixture-of-Experts Video Captioning Framework that Outperforms GPT-4V and Gemini-Pro-1.5 in General Scenes, Autonomous Driving, and Robotics Videos Researchers from NVIDIA, UC Berkeley, MIT, UT Austin, University of Toronto, and Stanford University have proposed Wolf, a

Wolf: A Mixture-of-Experts Video Captioning Framework that Outperforms GPT-4V and Gemini-Pro-1.5 in General Scenes, Autonomous Driving, and Robotics Videos

Researchers from NVIDIA, UC Berkeley, MIT, UT Austin, University of Toronto, and Stanford University have proposed Wolf, a
Pioneer Centre for AI (@aicentredk) 's Twitter Profile Photo

📢 On Thursday 22 August, Professor trevordarrell, from UC Berkeley Electrical Engineering & Computer Sciences (EECS), will give a Talk at The Museum of Natural History. Sign-up and find more information on our website: lnkd.in/exeY2nqb We look forward to seeing you.

📢 On Thursday 22 August, Professor <a href="/trevordarrell/">trevordarrell</a>, from <a href="/UCBerkeley/">UC Berkeley</a>  Electrical Engineering &amp; Computer Sciences (EECS), will give a Talk at The Museum of Natural History. 

Sign-up and find more information on our website: lnkd.in/exeY2nqb

We look forward to seeing you.
Sanjay Subramanian (@sanjayssub) 's Twitter Profile Photo

If you'll be at #ECCV2024 , check out our tutorial on Multimodal Foundation Models! boyiliee.github.io/lmfm/ When: Sunday, 9 AM to 12 PM Where (room): Brown 3 Who: Jitendra MALIK Boyi Li Saining Xie and me 😀