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)
Coding agents can now operate graphics tools. How will they change the way we design graphics algorithms and conduct graphics research? Join the discussion at the 1st Workshop on Agentic Graphics on Dec 1 afternoon at #SIGGRAPHAsia2026! 🔗 siga26.agentic-graphics.com
2
15
51
2,139
Video models can have high FPS while still feeling laggy if they respond to each action with high latency. FastFrames proposes two simple techniques to bring the latency down to 36 ms. Real-time video is not real until it responds in time!
For interactive video, FPS isn’t enough. Latency measures the actual responsiveness — from an input to an RGB output. FastFrames-1.3B generates frames in 35ms on a B200 GPU and FastFrames-14B in 45ms on 8 B200s. We also accelerate LingBot-1.3B to 50ms for responsive camera control. We open source all code and model weights. huggingface.co/papers/2611.2… apple-aiml-research.github.i…
15
590
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…
32
67
11
552
39,324
Our workshop has an exciting lineup of researchers from both academia and industry, including @MinhyukSung, @Papagina_Yi, @YuanLiu41955461, @peterchencyc, Professor Kai Wang, and Dr. Chunchao Guo.
4
76
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
22,552
Resist the flattening!
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!
2
1
561
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
148,412
Come to our session on Tuesday morning to learn more about how to make mesh generation fast and good!
Want a super-fast mesh generation model? ⚡ Don’t miss our MeshFlow talk! 📅 Tuesday 🕙 3D Generation session, starting around 10:45 AM 📍 Room 403B, LA Convention Center See you there! #SIGGRAPH #3DGeneration #MeshGeneration #SIGGRAPH2026 #DiffusionModel
4
634
I’ll be at #SIGGRAPH through Friday! Ping me if you’d like to chat about 3D generative models, world models, agentic graphics, or anything else!
1
5
519
🚀 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
8,592
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
There are three reasons why it's called "Functional Attention." 1⃣We make functions, instead of tokens, as first-class citizens for attention module. 2⃣It was inspired by the geometry processing concepts of functional maps. 3⃣It works!
What if attention wasn't about matching tokens, but operating in function space? Glad to share our #ICML2026 paper: 📄 Functional Attention: From Pairwise Affinities to Functional Correspondences w/ @Jiefang_Xiao @GaoMaolin @stevenygd Daniel Cremers 📄 xjffff.github.io/funcattn/
9
63
594
67,540
MeshFlow brings high-quality mesh with interactive speed. It's time to make mesh generation flow! Arxiv: arxiv.org/abs/2606.23489 Web: qiisun.github.io/MeshFlow/ Code: github.com/qiisun/MeshFlow
Excited to share MeshFlow — a new approach that can generate meshes with a fraction of seconds, while achieving state-of-the-art generation quality. Secret sources? Instead of autoregressive models, use equivariant flow-matching!
1
17
114
43,418
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
It’s #ECCV2026 review release (anywhere on earth) day! Good luck 🤞
2
11
2
119
33,041
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
488,657