william

World Model, Healthcare, Computer Vision, Cognitive Science;
Visiting @Tsinghua_Uni, Prev @Westlake_Uni

[william @WilliamH1B]

@eccvconf @jayinnn Would it be possible to briefly reopen the train ticket purchase? Didn’t receive any notification email about the ddl, and now the option is no longer available. Thank you!

[william @WilliamH1B]

@OpenAI Where is UBC? @UBC

[william @WilliamH1B]

What started as a messy research idea became an ECCV paper. GPT-5.6 helped me stress-test the hypothesis, catch weak assumptions, debug experiments, and sharpen the story—not by replacing the research, but by making every iteration faster and more rigorous.

[william @WilliamH1B]

@BaleCcchen Congrats on the oral!

[william @WilliamH1B]

@eccvconf Will reviewers be punished if they don’t submit the final review? Thanks 🙏🏼

[AI at Meta @AIatMeta]

Today we're introducing TRIBE v2 (Trimodal Brain Encoder), a foundation model trained to predict how the human brain responds to almost any sight or sound.

Building on our Algonauts 2025 award-winning architecture, TRIBE v2 draws on 500+ hours of fMRI recordings from 700+ people to create a digital twin of neural activity and enable zero-shot predictions for new subjects, languages, and tasks.

Try the demo and learn more here: https://t.co/VkMd1YpQWI

[Canada Comprehensive Security Check @CanadaSecCheck]

Over 100 affected families will gather at Parliament Hill on March 13 to speak out against long, unexplained PR delays. Many applicants have lived in Canada since their teenage years, built their education and careers here, yet their applications have been delayed for 2–3 years with no timeline or answers.

Family reunification has effectively stalled, and many children attending this protest are being forced to live apart from their parents because of these delays. Families are left in limbo, careers are on hold, and futures remain uncertain.

These endless delays are also pushing highly skilled, high-value talent to leave Canada.

We are calling on IRCC to provide transparency, clear timelines, and fair treatment for long-term residents who have already made Canada their home.

Learn more: https://t.co/ArNhjeyix7

[william @WilliamH1B]

@eccvconf Thanks a lot for the effort! It’s really kind :)

[william @WilliamH1B]

@eccvconf Thank you for your response and for forwarding to PC, we truly appreciate it. As first-time authors, we're not aware that completing the enrollment was also required, and we did not receive any reminder. We would be extremely grateful if a short extension could be considered.

[william @WilliamH1B]

@eccvconf Hi, we just realized there was no reminder about ECCV OpenReview enrollment, and some co-authors are currently asleep due to time zone differences. Could you please confirm whether there will be a grace period, or if this will result in a desk reject?

[Peter Yichen Chen @peterchencyc]

🌍 We are hiring! Would you please help us spread the word?
We welcome talents from every corner of the world — postdocs, PhD students, and paid, full-time research interns — to join us in exploring AI and physics simulation.
#3D #Robotics #Graphics #Hiring #UBC

[Peter Yichen Chen @peterchencyc]

It’s been a privilege to work with Yixin these past months—he has my full support.

https://t.co/tE1XACmABa

[Luma @LumaLabsAI]

✨ Introducing Imagine 3D: a new way to create 3D with text!
Our mission is to build the next generation of 3D and Imagine will be a big part of it. Today Imagine is in early access and as we improve we will bring it to everyone https://t.co/VIdilw7kpa

[william @WilliamH1B]

@kwea123 Do you think the same parameter works for every scene in your ngp_pl(llff)?

[william @WilliamH1B]

@kwea123 感觉新的那个accnerf就用到了depth-supervised的思想～

[Mark Boss @markb_boss]

As #ECCV2022 is approaching rapidly, I wanted to find all @neural_fields related papers. I've compiled my gatherings in another post of (hopefully) all NeRFy papers. Feel free to message me about anything I have missed :)

https://t.co/YfVIRzWJRa

[Ben Poole @poolio]

Happy to announce DreamFusion, our new method for Text-to-3D!

https://t.co/4xI2VHcoQW

We optimize a NeRF from scratch using a pretrained text-to-image diffusion model. No 3D data needed!

Joint work w/ the incredible team of @BenMildenhall @ajayj_ @jon_barron

#dreamfusion

[Devi Parikh @deviparikh]

Yes, it’s here :) Zero-shot text-to-video generation!

Introducing Make-A-Video.

The new SOTA, by a large margin, in text-to-video generation. And it doesn’t use any paired text-video data!

Examples, paper, and a sign up sheet at https://t.co/KRztukfN5B @MetaAI

Prompts 👇