Daniel Geng (@dangengdg) profile picture

Research @OpenAI, Sora videogen. Previously @UmichCSE, @GoogleDeepMind, @MetaAI, @berkeley_ai

Joined August 2016
Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)Photo by Daniel Geng (@dangengdg)
Can you make a jigsaw puzzle with two different solutions? Or an image that changes appearance when flipped? We can do that, and a lot more, by using diffusion models to generate optical illusions! Continue reading for more illusions and method details 🧵
16
113
38
612
126,045
Daniel Geng retweeted
🧐A question I've long been interested in: how can we learn from human hands and transfer that directly to robots? Our new work, HUG, makes it possible in three simple steps: (1) collect human grasps at scale, (2) learn from them, and (3) retarget for deployment.
5
24
2
117
10,748
Daniel Geng retweeted
We present MotionStream — real-time, long-duration video generation that you can interactively control just by dragging your mouse. All videos here are raw, real-time screen captures without any post-processing. Model runs on a single H100 at 29 FPS and 0.4s latency.
32
147
25
1,034
99,418
(1/n) Can pretrained video diffusion models be prompted to track pixels — without any retraining? We introduce Point-Prompting, a zero-shot point tracking method that simply prompts video models to visually mark and propagate points across time. 🌐 point-prompting.github.io
1
22
1
95
9,746
Daniel Geng retweeted
🐐🐐🐐Few people know Harold’s name, but he made lots of major breakthroughs of this new technology. Sora2 would be impossible without Harold!
Extremely honored to be part of this incredible team ❤️! Here is one of my favorite samples ; )
5
5
67
21,127
Daniel Geng retweeted
it's an honor to work with such an incredible group of researchers. massive shoutout to @LiLiunian, @DmytroOk , avi, @ezhang887 , @ryw999 @troyluhman and eric, eric mintun, @bram_wallace @JureZbontar @mmmbchang @gabriel1 @dangengdg and @cmikeh2 for their incredible work on sora 2. the sora research team is very special.
20
18
6
291
843,492
Daniel Geng retweeted
Sound on.
2,821
3,936
6,939
43,087
21,542,383
Daniel Geng retweeted
Sora 2 is here.
1,718
2,276
3,895
20,322
9,088,073
Daniel Geng retweeted
On the left is a rabbit. On the right is an elephant. But guess what: They’re the *same image* rotated 90°! In @currentbiology, @chazfirestone & I show how these images—known as “visual anagrams”—can help solve a longstanding problem in cognitive science. bit.ly/45BVnCZ
6
51
4
238
27,787
Excited to share our CVPR 2025 paper on cross-modal space-time correspondence! We present a method to match pixels across different modalities (RGB-Depth, RGB-Thermal, Photo-Sketch, and cross-style images) — trained entirely using unpaired data and self-supervision. Our approach learns correspondences through contrastive random walks across visual modalities. #CVPR2025 (1/6)
1
27
119
9,253
Daniel Geng retweeted
Ever wondered how a scene sounds👂 when you interact👋 with it? Introducing our #CVPR2025 work "Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes" -- we make 3D scene reconstructions audibly interactive! yimingdou.com/hearing_hands/
2
29
1
101
9,080
Daniel Geng retweeted
Can AI image detectors keep up with new fakes? Mostly, no. Existing detectors are trained using a handful of models. But there are thousands in the wild! Our work, Community Forensics, uses 4800+ generators to train detectors that generalize to new fakes. #CVPR2025 🧵 (1/5)
2
9
25
1,989
Hello! If you like pretty images and videos and want a rec for CVPR oral session, you should def go to Image/Video Gen, Friday at 9am: I'll be presenting "Motion Prompting" @RyanBurgert will be presenting "Go with the Flow" and @ChangPasca1650 will be presenting "LookingGlass"
3
16
65
5,493
Really cool paper about training interactivity into a video model with surprisingly little data! Great work!
Ever wish you could turn your video generator into a controllable physics simulator? We're thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. 🧵(1/n)
1
18
1,525
Ever wish YouTube had 3D labels? 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose! Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯 Download: huggingface.co/datasets/nvid…
2
38
5
173
43,332
A sister team to ours at Google DeepMind is looking for student researchers this summer. Please reach out if you are a PhD student working on media generation (diffusion models), or if you are a professor with students to recommend! 😀
9
22
1
161
24,348
Our workshop at #ICLR2025 is now open to submissions until 02/03 🥳 check our website if you are interested: sites.google.com/view/icbinb…
Our #ICLR2025 @iclr_conf workshop is looking for submissions on unexpected outcomes and hard-earned lessons in #DeepLearning Submission Deadline: 03 February 2025 Workshop Dates: 27 or 28 April 2025 Location: Singapore More info: shorturl.at/OpQns
1
1
896
Decentralized Diffusion Models power stronger models trained on more accessible infrastructure. DDMs mitigate the networking bottleneck that locks training into expensive and power-hungry centralized clusters. They scale gracefully to billions of parameters and generate photorealistic images with just a week of training on eight independent GPU nodes. They’re easy to implement, adopt DiT hyperparameters directly and outperform standard models FLOP-for-FLOP.
6
45
9
252
46,556
Hey all, I'll be answering questions about our "Motion Prompting" paper on alphaXiv (@askalphaxiv) (it's like arXiv, but adds a discussion section, and I think is quite well built!): alphaxiv.org/abs/2412.02700v…
1
8
49
5,404
I noticed I've been habitually using the same LLM over and over and I'm a bit worried I'm "overfit" so I made a website that randomly chooses from [Claude, Gemini, ChatGPT] for you: imfeelinglucky . chat (actual link + repo in thread)
2
23
2,151
url: imfeelinglucky.chat repo: github.com/dangeng/imfeeling… hopefully you find this useful! let me know if there are problems, if somebody has done this before, or if you have any other comments!
4
443