@TengdaHan

Research Scientist @GoogleDeepMind - Gemini video. Previously PhD @Oxford_VGG

 Oxford, England
tengdahan.github.io/
Joined March 2019
  • Tweets153
  • Following632
  • Followers1.6K
24Media
Gemini 4 Argon is amazing for knowledge work and coding - and it’s super fun to build with! We asked it to create this wizard chess game and it's so cool to see Argon's physics understanding & 3D modelling capabilities, makes me nostalgic for Battlechess on the Amiga - fun times! Argon is rolling out today to Google Ultra and Pro subscribers in the @GeminiApp and Search, and Ultra subscribers in @antigravity! More info & full availability in the blog: blog.google/innovation-and-a…
361
522
115
5,171
489,168
Introducing Gemini 4 Argon – our new frontier model. It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
1,986
4,641
4,530
42,895
9,005,138
Tengda Han retweeted
Junyu Xie@JunyuXieArthurSep 8
🎬 SLoMO is happening today! Join us this afternoon at the 2nd Story-Level Movie Understanding & Audio Description (SLoMO) Workshop at #ECCV2026! 📅 Today, Sept. 8, 2026 (afternoon, 2pm-6pm, CEST) 📍 Sportbaren / North Foyer, Malmö Arena 🌐 Website: slomo-workshop.github.io/ecc…
Junyu Xie@JunyuXieArthurJul 3
🎬 SLoMO is back! Ready to push the frontier of story-level movie understanding and Audio Description? Join us at the 2nd Story-Level Movie Understanding & Audio Description (SLoMO) Workshop at #ECCV2026 in Malmö, Sweden! 📅 Afternoon, Sept. 8, 2026 🌐 Website: slomo-workshop.github.io/ecc… 🏆 Competition details below 👇 MovieQA track: eval.ai/web/challenges/chall… Audio Description track: eval.ai/web/challenges/chall…
5
1
4
610
Agentic Video unlocks tons of possibilities!! Give it a try!
Ahmet Iscen@ahmetiusSep 1
Today, we're launching Agentic Video in Gemini! 🎬🤖 We’re bringing agentic capabilities directly to video in Gemini, enabling models to actively inspect, ground, and reason over temporal visual context. Excited to see what developers and researchers build with this!
18
1,625
Introducing Gemini 3.8 Flash, another upgrade in under a month! And the new 3.8 Flash Cyber pushes the frontier of cyber defense. Relentless progress 🚀 More on the models & our cyber security work in the blog - happy building! blog.google/innovation-and-a…

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.

blog.google
Logan Kilpatrick
@OfficialLoganKSep 2
Introducing Gemini 3.8 Flash, another jump in Gemini's agentic + coding capabilities, and our 3rd updated Flash model in only 6 weeks... This model has been a ton of fun to work with, excited to see what you all think!
213
211
23
3,333
209,312
Tengda Han retweeted
Google
@GoogleSep 1
We’re introducing a new capability to our latest Gemini models: agentic video understanding. This allows developers to process long-form video content with more accuracy, while using up to 88% less tokens. See how it works 🧵
201
489
182
5,806
794,128
Introducing Agentic Video in the Gemini API, a new way to process long videos which reduces token consumption by up to 88% while also increasing quality. This can be controlled easily in the API on a per video basis, available with our newest models like 3.7 Flash!
120
121
34
2,332
148,100
Tengda Han retweeted
koray kavukcuoglu
@koraykvAug 13
Today we're launching Gemini 3.7 Flash - our latest workhorse model for coding and agentic workflows, with an introductory price at half the original cost of 3.6 Flash. ⚡️ We have been iterating rapidly with the Flash series, going from 3.5 to 3.7 in just 3 months, making it more helpful across a wide range of tasks: • Software Engineering (DeepSWE v1.1): 37.0% ➔ 65.3% • Web Development (Code Arena Elo): 1506 ➔ 1588 • Enterprise Automation (AutomationBench): 13.4% ➔ 30.4%
119
240
105
2,362
597,734
Congratulations to the authors of "Efficiently Reconstructing Dynamic Scenes One D4RT at a Time", recipient of the #CVPR2026 Best Paper Award! 🏆 arxiv.org/pdf/2512.08924 @GoogleDeepMind
15
31
1
498
35,637
We will present “Seeing without Pixels” sites.google.com/view/seeing… at ExHall A, Poster #248, Sunday (today) from 15:30 to 17:30 @CVPR !! This work just won a CVPR Compute Transparency Champion award! Welcome to come by and say hi! #CVPR2026 #CVPR

Seeing without Pixels

Can you guess which action goes with which camera trajectory?

sites.google.com
Zihui (Sherry) Xue@sherryx900995972 Dec 2025
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 😊
1
20
1,698
Fun fact: the apartment we rented in Oxford Summertown from 2021-2023 has accommodated @elliottszwu (CVPR20 best paper awardee) and @jianyuan_wang (CVPR25 best paper awardee) as subletters. Now also @ChuhanZhang5 - new CVPR26 best paper awardee. Grateful to be at @Oxford_VGG !!
Chuhan Zhang@ChuhanZhang5Jun 5
Huge congrats to the team, D4RT is a team work and all the authors have been working very hard on this in the past one year. Very well deserved. 🍻 and thank you Award Committee Members for the recognition.
3
6
3
88
13,530
Congratulations to @ChuhanZhang5 and the team @GoogleDeepMind !!!
Chuhan Zhang@ChuhanZhang5Jun 5
Huge congrats to the team, D4RT is a team work and all the authors have been working very hard on this in the past one year. Very well deserved. 🍻 and thank you Award Committee Members for the recognition.
20
2,051
Tengda Han retweeted
#CVPR2026@CVPRJun 5
Announcing the official #CVPR2026 Best Paper Award Winner! 🏆 Congratulations to the authors for their landmark contributions to the field!👏👏
4
64
11
487
160,109
Accepted by @CVPR #CVPR2026 🎉🎉 Congratulations @sherryx90099597
Tengda Han@TengdaHan1 Dec 2025
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.
6
77
7,907
Accepted by @CVPR #CVPR2026 🎉🎉
Tengda Han@TengdaHan4 Dec 2025
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.
1
6
35
4,504
Gemini 3.1 Pro is here. We’ve significantly improved the model’s overall intelligence so it can solve tougher problems. 🧵
285
706
299
6,158
929,287
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/1qTv…

Student Researcher Position at Google DeepMind on Audio-Visual Models (Summer 2026)

I am seeking highly motivated PhD students with a background in audio and video. Please proceed with filling out the form only if you meet these criteria: 1) PhD student 2) Have at least 1-2 public...

docs.google.com
1
19
1
125
11,887
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@ChuhanZhang510 Dec 2025
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
5
20
202
17,717
Tengda Han retweeted
Weidi Xie@WeidiXie10 Dec 2025
🚀 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/SceneGe… 🔗 Model: huggingface.co/haoningwu/Sce… 🌐 WebPage: mengmouxu.github.io/SceneGen #3DVision #AI #GenerativeAI #ComputerVision #3DV2026 #SceneGen
1
2
1
7
937
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@TengdaHan4 Dec 2025
Replying to @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

Unique Lives, Shared World: Learning from Single-Life Videos

We introduce the "single-life" learning paradigm, where we train a distinct vision model exclusively on egocentric videos captured by one individual. We leverage the multiple viewpoints naturally...

arxiv.org
2
4
15
2,483
Load more