Guandao Yang (@GuandaoYang) header
Guandao Yang (@GuandaoYang) profile picture

Assistant Professor @ UT Austin. Researcher @ Apple. Stanford Postdoc. Cornellian. Building generative models for the physical world.

Austin
Joined March 2015
Photo by Guandao Yang (@GuandaoYang)Photo by Guandao Yang (@GuandaoYang)Photo by Guandao Yang (@GuandaoYang)Photo by Guandao Yang (@GuandaoYang)Photo by Guandao Yang (@GuandaoYang)Photo by Guandao Yang (@GuandaoYang)
Guandao Yang retweeted
Apple just released FastFrames Video Generation at Interactive Latency FastFrames-L (14B): huggingface.co/apple/FastFra… FastFrames-S (1.3B): huggingface.co/apple/FastFra…
33
69
12
558
40,298
Guandao Yang retweeted
1/7 Excited to share SceneRig! 🦾 One image → an editable, simulation-ready 3D scene. We combine AI agents with geometry and physics to reconstruct scenes for robot policy evaluation and replay of real-world manipulations. Here’s how it works 🧵👇
6
17
7
161
22,562
Guandao Yang retweeted
Everyone's asking what humans are still worth in the age of AI. To me, it's the part of us that AI keeps flattening - our individuality. Yet I feel I'm constantly being sold a choice: extend myself with AI, or preserving my unique thoughts, tastes and opinions. What if I didn't have to choose? There is a future where we get the magic of feeling totally understood by the technology that serves us, while staying ourselves. In this future, the model of us -- our "second selves" -- must be owned by us. That's the future we want to live in, and one we're building at Aesona. The open, top-of-mind questions right now: 1. What's the right representation of a person and how should it evolve over time? 2. How do we measure individual-level alignment? How should you interact with the model to close gaps in what it doesn't yet know about you? 3. What should your second self refuse to say about you? How should the user create the right "disclosure policy" and how should it be enforced? If this sounds like a future you want to build, my DMs are open!
We should all be asking who — or what — owns our minds. A model that understands what makes you you can be incredibly enabling and deeply dangerous. That's why we think a "second self" — a model whose only job is to understand you and make your life better — must be owned by you. A faithful second self, in both senses, is the foundation of personal AI. Our founding thesis, below.
15
16
11
65
148,419
🚀 Excited to kick off the Graphics × Science Workshop at #SIGGRAPH2026! Computer graphics is becoming a foundational tool for scientific discovery. From computational imaging and molecular modeling to physical simulation, robotics, manufacturing, and AI, graphics is helping us model, understand, and design the physical world. Looking forward to an exciting program featuring 3 keynote speakers and 58 highlighted papers. 🔗 graphics4science.github.io/2… #AI4Science #ComputerGraphics #ScientificComputing #Simulation #NVIDIA #NVIDIAOmniverse #NVIDIAAI
2
11
3
40
8,596
Guandao Yang retweeted
Excited to share 𝐄𝐫𝐫𝐨𝐫-𝐂𝐨𝐧𝐝𝐢𝐭𝐢𝐨𝐧𝐞𝐝 𝐍𝐞𝐮𝐫𝐚𝐥 𝐒𝐨𝐥𝐯𝐞𝐫𝐬 (𝐄𝐍𝐒), a PDE framework that recurrently corrects its own prediction by reading the PDE residual field rather than minimizing it! Website: neuralsolver.github.io/
1
2
7
856
The call for the #ECCV2026 Doctoral Consortium is now available. Details: eccv.ecva.net/Conferences/20…
1
2
12
7,632
The #ECCV2026 reviewer discussion period has started! Reviewers should carefully read the authors’ rebuttal, consider the other reviews, and actively participate in the discussion BEFORE finalizing their reviews.
🤖 Made with AI
1
3
2
22
15,259
What’s New at #ECCV2026 Malmo 🇸🇪? Please read the important policy updates (especially with regard to ECCV 2024) on our “What’s new?” page. Notably, this year, we introduced “Contribution Types”, a mechanism for tagging submissions &reviewers to facilitate fair evaluation. 1/2
2
8
28
9,641
The #ECCV2026 Malmo 🇸🇪 call for papers is now available. Check it out!
1
6
36
4,702
Guandao Yang retweeted
Combining the benefits of RL and SFT with on-policy distillation, a promising approach for training small models for domain performance and continual learning.
Our latest post explores on-policy distillation, a training approach that unites the error-correcting relevance of RL with the reward density of SFT. When training it for math reasoning and as an internal chat assistant, we find that on-policy distillation can outperform other approaches for a fraction of the cost. thinkingmachines.ai/blog/on-…
99
214
32
2,795
488,661
Guandao Yang retweeted
We've released all code and models for FlashDepth! It produces depth maps from a 2k, streaming video in real-time. This was a really fun course project inspired by discussions with @mohsaied and @stevenygd and we look forward to presenting it at #ICCV2025. GitHub: github.com/Eyeline-Research/… Project page: eyeline-research.github.io/F…
The latest research paper from @eyelinestudios, FlashDepth, has been accepted to the International Conference on Computer Vision (#ICCV2025). Our model produces accurate and high-resolution depth maps from streaming videos in real time and is completely built on open-source models and data. We hope it will be applied to various online applications, like robotics and on-set video composition. It has already been integrated into a few internal tools for visual effects and real-time depth estimation, segmentation, and matting tasks. Congrats to the team: @gene_ch0u, @wenqi_xian, @stevenygd, @mohsaied, @Bharathharihar3, @Jimantha, @realNingYu, @debfx ! All models and code have been released: GitHub: github.com/Eyeline-Research/… Project page: eyeline-research.github.io/F… Paper: arxiv.org/abs/2504.07093
6
66
2
543
38,024
For those at CVPR, Aditya will be presenting this poster tomorrow at 10:30 (Exhibit hall D, Poster #34). Come hear about why neural field derivatives are noisy, and how we resurrect image processing ideas for neural fields!
📢 Excited to share our latest work on computing accurate differential operators for hybrid neural fields (like Instant NGP)! 🔗: justachetan.github.io/hnf-de… 🧵👇🏻 (1/n)
3
8
1,538
Guandao Yang retweeted
Most video models struggle to feel like real worlds. They forget what’s just out of view, slow down as videos get longer, or breaks causality. We think State Space Models are a natural fit for models with: 🧠 long-term memory across hundreds of frames ⚡ constant-speed generation, even for long rollouts ⏩ fully causal dynamics, fit for real-time interaction
Long-Context State-Space Video World Models "we propose a novel architecture leveraging state-space models (SSMs) to extend temporal memory without compromising computational efficiency. "
2
11
1
51
5,316
Introducing AIpparel @CVPR 2025 - the first multimodal foundation model for digital garments. georgenakayama.github.io/AIp… 1/6
1
23
2
176
12,888
How can we use wide-FOV cameras for reconstruction? We propose self-calibration Gaussian Splatting that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations to directly reconstruct from a set of wide-angle captures. page: denghilbert.github.io/self-c…
2
35
183
13,241
Do large multimodal models understand how to make dresses for your winter holiday party💃? We introduce AIpparel, a vision-language-garment model capable of generating and editing simulation-ready sewing patterns from text and images. Project page at georgenakayama.github.io/AIp…. [1/n]
1
18
1
68
11,938
Guandao Yang retweeted
🚀 Introducing CausVid: Instant video generation that plays the moment you hit "Generate", while maintaining state-of-the-art quality! Project Page: causvid.github.io. More details in the long thread.
3
28
8
158
28,618
Guandao Yang retweeted
[Hiring!] I am hiring multiple PhDs @CSatUSC @USCViterbi for this cycle. If you're interested in scene representations, neural simulation, generative AI, and robotics, feel free to mention my name in your application (no need to email). For USC masters/undergrads who're interested in our research, feel free to fill in this form forms.gle/RerZfDqCqmCj8As27.
1
47
3
268
32,855
Guandao Yang retweeted
A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
16
201
28
941
173,500
Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired context—character consistency, item/asset adaptation, scene relighting, and more. It even enables the creation of comics/mangas without any effort in fine-tuning or training a personalized model! 📰 Paper: arxiv.org/abs/2411.18616 🌐 Website: primecai.github.io/dsd/ Team effort with @ericryanchan, @zhang_yunzhi, @GuibasLeonidas, @jiajunwu_cs, and @GordonWetzstein.
24
73
7
431
60,888