Senior Research Scientist @GoogleDeepMind, core contributor of Gemini Large-Scale Pretraining and Omni Post-training; Prev: PhD @CornellCIS, BS @Tsinghua_Uni
New York City
Joined June 2015
- Tweets214
- Following2.8K
- Followers1.7K
- Likes10.9K
Luming Tang retweeted
Gemini 4 Carbon is now available for users, developers and enterprises!
We are heavily using Carbon internally at Google for hardest long horizon tasks, our teams have used it to help mathematically prove the core cryptographic protocol of Signal — and it’s topping independent benchmarks like CursorBench 4.0, Perplexity’s WANDR, Zapier’s AutomationBench, and more.
The team also had fun using Carbon to analyze images and technical drawings from humanity’s first crewed lunar lander, the Apollo Lunar Module. Not a single flown component ever returned to Earth. It recreated the 3D asset from those historic documents and generated this walkthrough video.
Read more: blog.google/innovation-and-a…
Luming Tang retweeted
Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬
Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale:
⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K
⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s
💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch
🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync
🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts
See these updates in action ↓
Luming Tang retweeted
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!
Come work with our LSP team. Zack is amazing!
The Gemini Large Scale Pretrain team is hiring a Research Engineer in London or MTV! The team works across the pretrain stack: research codebases, distributed training infra, data pipelines, tooling for training dynamics analysis, and most importantly using Gemini to accelerate our work! 🚀
If you're an engineer who has a strong "whatever it takes" attitude and is not afraid of spending tokens, apply here with some showcase work: google.com/about/careers/app…
No particular qualifications needed, and we welcome early career applicants. Join if you want me to bug you with refactors to enable [new AGI compute multiplier]! 👀
3
18
1,187
Luming Tang retweeted
📢Thrilled to share that I'll be joining Harvard and the Kempner Institute as an Assistant Professor starting Fall 2026!
I'll be recruiting students this year for the Fall 2026 admissions cycle. Hope you apply!
We are thrilled to share the appointment of @QianqianWang5 as an #KempnerInstitute Investigator! She will bring her expertise in computer vision to @Harvard.
Read the announcement: bit.ly/4mIghHy
@hseas #AI #ComputerVision
Luming Tang retweeted
📢Excited to share that I’ve joined @MBZUAI as an Assistant Professor of Computer Vision this fall!
If you’re interested in CV4Science: building the next generation of foundation models & discovery tools for science, consider applying to MBZUAI. I’ll be recruiting PhD students!
After a year of severe injury and complex surgery, I wrote about my journey—physical, emotional, and everything in between—hoping it might help others feel less alone in their own recovery.
tender-aster-768.notion.site…
These demos look so amazing!
Bored of linear recurrent memories (e.g., linear attention) and want a scalable, nonlinear alternative?
Our new paper “Test-Time Training Done Right” propose LaCT (Large Chunk Test-Time Training) — a highly efficient, massively scalable nonlinear memory with:
💡 Pure PyTorch (no custom kernels)
🚀 10× GPU FLOPs utilization compared to previous nonlinear test-time training(ttt) methods.
🧠 Huge memory size (up to 40% of model params)
Project page with code: tianyuanzhang.com/projects/t…
(videos generated with our AR video diffusion)
1/9
1
1,522
Congrats to my great roommate during PhD, who got best paper award when I was still trying to figure out how to write an organized vision paper 😆 Yucheng is so nice, kind, and have so much passion and insights on research. I cannot imagine how lucky his first batch students are
This quoted post is unavailable.
14
1,633
Really cool work on using MLLM to analyze city-scale image collection and automatically find the changes over time. Really curious to see all the interesting findings discovered by it!
Curious about how cities have changed in the past decade? We use MLLMs to analyse 40 million Street View images to answer this. Do you know that "juice shops became a thing in NYC" and "miles of overpasses were painted BLUE in SF"? More at→boyangdeng.com/visual-chroni… (vid ↓ w/ 🔊)
really cool work and demo！
Thrilled to introduce Video Depth Anything to support Depth Estimation for super-long videos (over 5 minutes).
👉It enjoys all the benefits of #DepthAnything: high-quality, fast, robust, etc.
Proj Page: videodepthanything.github.io…
2
859
Luming Tang retweeted
github.com/NVIDIA/Cosmos
Cosmos is a developer-first platform designed to help physical AI builders accelerate their development. It has pre-trained world foundation models (diffusion & autoregressive) in different sizes and video tokenizers. They are open models with permissive licenses. Try it out, and let us know how we can better help.
Luming Tang retweeted
and also check out paper, which might be the first wave to explore this idea, "Diffusion Models Without Attention" (arxiv.org/abs/2311.18257) with @thoma_gu and @srush_nlp.
Luming Tang retweeted
Why can’t more non-Chinese researchers show even a bit care about the racism against Chinese students in the NeurIPS keynote?
Why can’t more US researchers pay any attention to the suffering of international students?
I remain very disappointed, esp. at many established people.
Interesting recording. And thanks to the audience for confronting straightforward!
Someone confronted on the spot, and they said “ Maybe there is one, maybe they are common, who knows what. I hope it was an outlier.” Even this explanation is full of implicit racial bias. See the full conv: dropbox.com/scl/fi/2dtji0z84…
11
1,811
Apparently, this is called “cultural generalization” according to #NeurIPS2024 . Never too old to learn something new.
1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feeling uncomfortable. As a community, I believe we should take a moment to reflect on why such remarks in public discourse can be offensive and harmful.
Cultural generalization? Come on bro
NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address the comment made during the invited talk this afternoon, as it is something that NeurIPS does not condone and it doesn't align with our code of conduct. We are addressing this issue with the speaker directly.
NeurIPS is dedicated to being a diverse and inclusive place where everyone is treated equally.
6
1,128
