Tengda Han (@TengdaHan) - Twitter Profili | Zamantika Mersobahis Locabet

Tengda Han@TengdaHan·26 Şub

Accepted by @CVPR #CVPR2026 🎉🎉 Congratulations @sherryx90099597

Human perception is active: we move around to see, and we see with intention. In our latest work "Seeing without Pixels", we find "how you see" (how the camera moves) roughly reveals "what you do" or "what you observe" -- and this connection can be easily learned from data.

English

0

6

77

7.3K

Tengda Han@TengdaHan·26 Şub

Accepted by @CVPR #CVPR2026 🎉🎉

Tengda Han@TengdaHan

Human learns from unique data -- everyone's OWN life -- but our visual representations eventually align. In our recent work "Unique Lives, Shared World" @GoogleDeepMind, we train models with "single-life" videos from distinct sources, and study their alignment and generalisation.

English

1

5

35

4.1K

Tengda Han retweetledi

Google DeepMind@GoogleDeepMind·19 Şub

Gemini 3.1 Pro is here. We’ve significantly improved the model’s overall intelligence so it can solve tougher problems. 🧵

GIF

English

287

751

6.3K

916K

Tengda Han@TengdaHan·24 Oca

@TongPetersb Thanks for sharing! Nice blog!

English

0

4

308

Peter Tong@TongPetersb·24 Oca

We have been training with TPUs in academia for two years now (huge thanks to Google TRC!). Works like Cambrian-1, Cambrian-S, RAE, and Scale-RAE would not have been possible without TPUs. We wrote a blog post sharing our experiences, optimizations, and lessons learned: cambrian-mllm.github.io/blog/tpu-train… We hope this can help more people having a smoother experience working with TPUs, they are very powerful!

English

9

25

269

37.4K

Tengda Han retweetledi

Sayna Ebrahimi@SaynaEbrahimi·10 Ara

I’m looking for PhD students in Audio & Video for a Summer 2026 internship at Google DeepMind! ⚠️ Requirement: Prior publication in this area. To apply, tell me the most critical research gap in AV understanding to see if we are a match! docs.google.com/forms/d/1qTvfE…

English

1

19

126

11.5K

Tengda Han@TengdaHan·10 Ara

A SOTA model on 4D reconstruction from @GoogleDeepMind! Amazing work from @ChuhanZhang5 and the team! It was so satisfactory to see these reconstruction results and I've been having a great experience using it

Chuhan Zhang@ChuhanZhang5

A SINGLE encoder + decoder for all the 4D tasks! We release 🎯 D4RT (Dynamic 4D Reconstruction and Tracking). 📍 A simple, unified interface for 3D tracking, depth, and pose 🌟 SOTA results on 4D reconstruction & tracking 🚀 Up to 100x faster pose estimation than prior works

English

5

20

202

17.6K

Tengda Han retweetledi

Weidi Xie@WeidiXie·10 Ara

🚀 Glad to share the exciting project — SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass! We explored the generation of 3D scenes with multiple assets from a single image. 🎉 ACCEPTED by 3DV 2026!!! All resources have been open-sourced and publicly available! 📄 Paper: arxiv.org/abs/2508.15769 💻 Code: github.com/Mengmouxu/Scen… 🔗 Model: huggingface.co/haoningwu/Scen… 🌐 WebPage: mengmouxu.github.io/SceneGen #3DVision #AI #GenerativeAI #ComputerVision #3DV2026 #SceneGen

English

1

2

7

815

Tengda Han retweetledi

joao carreira@joaocarreira·5 Ara

Future AI models will learn predominantly post-deployment – to do the tasks of interest to each user. This will happen throughout an individual “life”. In a new paper arxiv.org/pdf/2512.04085 we lay out groundwork for this type of capabilities in the wild from a visual standpoint.

Tengda Han@TengdaHan

Work from @SaynaEbrahimi, myself, and @dilaragoekay, @goolygu, Maks Ovsjanikov, Iva Babukova, @DanielZoran_ , Viorica Patraucean, @joaocarreira , Andrew Zisserman and @dimadamen at @GoogleDeepMind. Arxiv: arxiv.org/abs/2512.04085

English

2

4

15

2.4K

Tengda Han@TengdaHan·5 Ara

Work from @SaynaEbrahimi, myself, and @dilaragoekay, @goolygu, Maks Ovsjanikov, Iva Babukova, @DanielZoran_ , Viorica Patraucean, @joaocarreira , Andrew Zisserman and @dimadamen at @GoogleDeepMind. Arxiv: arxiv.org/abs/2512.04085

English

1

2

13

3.1K

Tengda Han@TengdaHan·5 Ara

Human learns from unique data -- everyone's OWN life -- but our visual representations eventually align. In our recent work "Unique Lives, Shared World" @GoogleDeepMind, we train models with "single-life" videos from distinct sources, and study their alignment and generalisation.

English

10

30

147

12.6K

Tengda Han@TengdaHan·3 Ara

Sherry is currently on the industry job market. Highly recommend!!

Zihui (Sherry) Xue@sherryx90099597

Excited to share our latest work! Grateful for the guidance from all my collaborators, and special thanks to Tengda for being such an amazing mentor during my internship @GoogleDeepMind 😊

English

1

10

3.2K

Tengda Han@TengdaHan·2 Ara

@KevinQHLin @sherryx90099597 @dimadamen Thanks for reposting!

English

0

1

109

Kevin Lin@KevinQHLin·2 Ara

Interesting idea! trajectory vector being a new representation for activity understanding great work by @sherryx90099597 @dimadamen @TengdaHan

Dmytro Mishkin 🇺🇦@ducha_aiki

Seeing without Pixels: Perception from Camera Trajectories @sherryx90099597 Kristen Grauman @dimadamen Andrew Zisserman @TengdaHan tl;dr: in title. I love such "blind baseline" papers. arxiv.org/abs/2511.21681

English

2

0

11

2.5K

Tengda Han@TengdaHan·2 Ara

@ducha_aiki @sherryx90099597 @dimadamen Thank you Dmytro for reposting! Glad you like it :)

English

0

4

234

Dmytro Mishkin 🇺🇦@ducha_aiki·1 Ara

Seeing without Pixels: Perception from Camera Trajectories @sherryx90099597 Kristen Grauman @dimadamen Andrew Zisserman @TengdaHan tl;dr: in title. I love such "blind baseline" papers. arxiv.org/abs/2511.21681

English

1

14

103

7.5K

Tengda Han@TengdaHan·2 Ara

Project page for more details and qualitative examples: sites.google.com/view/seeing-wi… Sherry will be at @NeurIPSConf this week! Catch her to chat more!

English

0

7

638

Tengda Han@TengdaHan·2 Ara

Can you tell which action corresponds to which camera trajectory in the video above? Check out our paper for answers! Work done by our great intern Sherry Xue @sherryx90099597 at @GoogleDeepMind, and with Kristen Grauman, @dimadamen and Andrew Zisserman. arxiv.org/abs/2511.21681

English

1

2

13

1.3K

Tengda Han@TengdaHan·2 Ara

Human perception is active: we move around to see, and we see with intention. In our latest work "Seeing without Pixels", we find "how you see" (how the camera moves) roughly reveals "what you do" or "what you observe" -- and this connection can be easily learned from data.

English

2

18

165

20.8K

Tengda Han@TengdaHan·1 Ara

A belated post for our ACMMM paper: we recognize and track animated characters for movie understanding tasks. Great work from Zhongrui Gui, also with @JunyuXieArthur @WeidiXie and Andrew Zisserman from @Oxford_VGG . Project page with code and dataset: robots.ox.ac.uk/~vgg/research/…

English

0

1

187

Tengda Han@TengdaHan·1 Ara

Animated movies can be effortlessly understood by young minds, but appear to be challenging for video-language models, why? The key problem is the huge diversity of animated characters -- their appearance ranges from human-like faces, to cars, fish, blobs, etc.

English

1

3

13

2K

Tengda Han@TengdaHan·19 Eki

The SLoMo workshop on "Story-level Movie Understanding & Audio Description" will be on #ICCV2025 day-1 morning, starting at 8:40 AM at Room 327! @JunyuXieArthur, @maxhbain and Xi will be there in person. See you tomorrow @ICCVConference !! #iccv25

Tengda Han@TengdaHan

Being able to understand, describe and even enjoy movies is one of the pinnacles of computer vision. Interested in movie understanding and audio description? Check out our SLoMo workshop at @ICCVConference #ICCV2025!!

English

1

6

47

9.9K

Tengda Han@TengdaHan·7 Tem

Being able to understand, describe and even enjoy movies is one of the pinnacles of computer vision. Interested in movie understanding and audio description? Check out our SLoMo workshop at @ICCVConference #ICCV2025!!

Junyu Xie@JunyuXieArthur

Movies are more than just video clips, they are stories! 🎬 We’re hosting the 1st SLoMO Workshop at #ICCV2025 to discuss Story-Level Movie Understanding & Audio Descriptions! Website: slomo-workshop.github.io Competition: huggingface.co/spaces/SLoMO-W…

English

0

2

20

9.9K

Tengda Han

Keşfet