Tzu-Mao Li
@tzumaoli.bsky.social
https://cseweb.ucsd.edu/~tzli/
computer graphics, programming systems, machine learning, differentiable graphics
computer graphics, programming systems, machine learning, differentiable graphics
I gave a talk at Pacific Graphics 2025 on the topic of "Classical Computer Graphics in the Age of Generative AI". I've uploaded the recording to Youtube today.
www.youtube.com/watch?v=Vyci...
www.youtube.com/watch?v=Vyci...
"Classical Computer Graphics in the Age of Generative AI", Pacific Graphics 2025 Keynote, Tzu-Mao Li
YouTube video by Tzu-Mao Li
www.youtube.com
October 30, 2025 at 7:53 PM
I gave a talk at Pacific Graphics 2025 on the topic of "Classical Computer Graphics in the Age of Generative AI". I've uploaded the recording to Youtube today.
www.youtube.com/watch?v=Vyci...
www.youtube.com/watch?v=Vyci...
Reposted by Tzu-Mao Li
🎄 Introducing our paper A Generalizable Light Transport 3D Embedding for Global Illumination lnkd.in/gQUMSAyV .
🙈 Just as Transformers learn long-range relationships between words or pixels, our new paper shows they can also learn how light interacts and bounces around a 3D scene.
🙈 Just as Transformers learn long-range relationships between words or pixels, our new paper shows they can also learn how light interacts and bounces around a 3D scene.
October 23, 2025 at 3:27 AM
🎄 Introducing our paper A Generalizable Light Transport 3D Embedding for Global Illumination lnkd.in/gQUMSAyV .
🙈 Just as Transformers learn long-range relationships between words or pixels, our new paper shows they can also learn how light interacts and bounces around a 3D scene.
🙈 Just as Transformers learn long-range relationships between words or pixels, our new paper shows they can also learn how light interacts and bounces around a 3D scene.
Reposted by Tzu-Mao Li
Today we're unveiling our newest project: OpenQMC! Developed & contributed to the Foundation by @framestore.bsky.social, OpenQMC aims to improve the fidelity & efficiency of rendering photoreal moving images for film, TV, gaming & advertising. Read more on our blog:
www.aswf.io/blog/openqmc...
www.aswf.io/blog/openqmc...
OpenQMC Becomes an Academy Software Foundation Project - ASWF
Developed by Framestore, OpenQMC has improved the fidelity and speed of rendering Hollywood blockbusters such as Barbie, Superman, Wicked, F1 the Movie and How to Train Your Dragon LOS ANGELES, CA, Oc...
www.aswf.io
October 7, 2025 at 4:16 PM
Today we're unveiling our newest project: OpenQMC! Developed & contributed to the Foundation by @framestore.bsky.social, OpenQMC aims to improve the fidelity & efficiency of rendering photoreal moving images for film, TV, gaming & advertising. Read more on our blog:
www.aswf.io/blog/openqmc...
www.aswf.io/blog/openqmc...
Anything outside of Nyquist-Shannon limit is "hallucination". It used to have cooler names aliasing/noise. I think the key difference between the two is that human are good at catching aliasing/noise (even anti-aliasing), but not good at noticing hallucination. So "hallucination" feels like cheating
September 15, 2025 at 9:32 PM
Anything outside of Nyquist-Shannon limit is "hallucination". It used to have cooler names aliasing/noise. I think the key difference between the two is that human are good at catching aliasing/noise (even anti-aliasing), but not good at noticing hallucination. So "hallucination" feels like cheating
Reposted by Tzu-Mao Li
My lab will be recruiting at all levels. PhD students, postdocs, and a research engineering position (worldwide for PhD/postdoc, EU candidates only for the engineering position). If you're at SIGGRAPH, I'd love to talk to you if you are interested in any of these.
August 8, 2025 at 8:09 AM
My lab will be recruiting at all levels. PhD students, postdocs, and a research engineering position (worldwide for PhD/postdoc, EU candidates only for the engineering position). If you're at SIGGRAPH, I'd love to talk to you if you are interested in any of these.
Reposted by Tzu-Mao Li
"Hallucinations on the future of real-time rendering", High Performance Graphics 2025 keynote: c0de517e.com/023_hpg.htm
Hallucinations on the future of real-time rendering.
Angelo Pesce's homepage & blog on computers, graphics and other things.
c0de517e.com
July 13, 2025 at 2:39 PM
"Hallucinations on the future of real-time rendering", High Performance Graphics 2025 keynote: c0de517e.com/023_hpg.htm
Rendering nerds! Check out our latest work "Vector-Valued Monte Carlo Integration Using Ratio Control Variates" that has just gotten the best paper award at SIGGRAPH 2025. This paper presents a method that reduces variance of a wide range of rendering and diff. rendering tasks with negligible cost.
June 14, 2025 at 5:26 PM
Rendering nerds! Check out our latest work "Vector-Valued Monte Carlo Integration Using Ratio Control Variates" that has just gotten the best paper award at SIGGRAPH 2025. This paper presents a method that reduces variance of a wide range of rendering and diff. rendering tasks with negligible cost.
Reposted by Tzu-Mao Li
An update, a bit of retrospection, and a call for you, yes, you, to help JCGT a bit: www.realtimerendering.com/blog/jcgt-is...
JCGT is moving along | Real-Time Rendering
www.realtimerendering.com
May 16, 2025 at 5:34 PM
An update, a bit of retrospection, and a call for you, yes, you, to help JCGT a bit: www.realtimerendering.com/blog/jcgt-is...
zeamoxwang.github.io/HotSpot-CVPR...
My student Zimo/Cheng's recent work tackles this problem! A lot of recent neural "SDF" optimizers use losses that, even when perfectly minimized, still don't result in actual signed distance fields. Our loss guarantees convergence to distance when minimized.
My student Zimo/Cheng's recent work tackles this problem! A lot of recent neural "SDF" optimizers use losses that, even when perfectly minimized, still don't result in actual signed distance fields. Our loss guarantees convergence to distance when minimized.
March 29, 2025 at 9:08 PM
zeamoxwang.github.io/HotSpot-CVPR...
My student Zimo/Cheng's recent work tackles this problem! A lot of recent neural "SDF" optimizers use losses that, even when perfectly minimized, still don't result in actual signed distance fields. Our loss guarantees convergence to distance when minimized.
My student Zimo/Cheng's recent work tackles this problem! A lot of recent neural "SDF" optimizers use losses that, even when perfectly minimized, still don't result in actual signed distance fields. Our loss guarantees convergence to distance when minimized.
Reposted by Tzu-Mao Li
Announcing SGI 2025! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu
January 6, 2025 at 3:48 PM
Announcing SGI 2025! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu
Reposted by Tzu-Mao Li
live in about 10 hours from now - subscribe/mark your calendars/tell your friends/share etc. c:
Generative AI is a Parasitic Cancer
www.youtube.com/watch?v=-opB...
Generative AI is a Parasitic Cancer
www.youtube.com/watch?v=-opB...
Generative AI is a Parasitic Cancer
YouTube video by Freya Holmér
www.youtube.com
January 2, 2025 at 11:13 AM
live in about 10 hours from now - subscribe/mark your calendars/tell your friends/share etc. c:
Generative AI is a Parasitic Cancer
www.youtube.com/watch?v=-opB...
Generative AI is a Parasitic Cancer
www.youtube.com/watch?v=-opB...
Reposted by Tzu-Mao Li
Shannon Woods from NVIDIA gave a great presentation on Slang at SIGGRAPH Asia. The slides and video are available on the event page: www.khronos.org/events/siggr...
December 20, 2024 at 3:06 PM
Shannon Woods from NVIDIA gave a great presentation on Slang at SIGGRAPH Asia. The slides and video are available on the event page: www.khronos.org/events/siggr...
Reposted by Tzu-Mao Li
AI Compiler research intern positions at NVIDIA (Seattle). Functional programming, polyhedral compilation, program synthesis, compiler optimization. Send resume to compiler-jobs@Nvidia.com
December 16, 2024 at 7:40 PM
AI Compiler research intern positions at NVIDIA (Seattle). Functional programming, polyhedral compilation, program synthesis, compiler optimization. Send resume to compiler-jobs@Nvidia.com
Reposted by Tzu-Mao Li
I'm keeping updated this super comprehensive collection of papers (by tech and by year), from the Kajiya eq to latest differential and neural approaches, passing by RRT and MC theories | As before, repost if you think it may be useful to others.
drive.google.com/drive/folder...
drive.google.com/drive/folder...
November 21, 2024 at 9:38 PM
I'm keeping updated this super comprehensive collection of papers (by tech and by year), from the Kajiya eq to latest differential and neural approaches, passing by RRT and MC theories | As before, repost if you think it may be useful to others.
drive.google.com/drive/folder...
drive.google.com/drive/folder...
Reposted by Tzu-Mao Li
SGP 2025 will take place in Bilbao between June 30th and July 4th, and I am one of the Technical Program Co-Chairs. For the first time, we are introducing an *early* paper deadline on **February 7th**!
December 10, 2024 at 6:42 PM
SGP 2025 will take place in Bilbao between June 30th and July 4th, and I am one of the Technical Program Co-Chairs. For the first time, we are introducing an *early* paper deadline on **February 7th**!
Reposted by Tzu-Mao Li
If you're interested in a PhD at the intersection of machine learning and programming languages, consider applying to Yale CS!
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
December 8, 2024 at 4:27 PM
If you're interested in a PhD at the intersection of machine learning and programming languages, consider applying to Yale CS!
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
We're exploring new approaches to building software that draws inferences and makes predictions. See alexlew.net for details & apply at gsas.yale.edu/admissions/ by Dec. 15
cseweb.ucsd.edu/~tzli/Score_...
I wrote down some random notes about the connection between score matching (aka diffusion models) and Stein's unbiased risk estimate (SURE). It shows why optimal denoising lead to optimal score. Not a new observation but doesn't seem to be talked enough in literature.
I wrote down some random notes about the connection between score matching (aka diffusion models) and Stein's unbiased risk estimate (SURE). It shows why optimal denoising lead to optimal score. Not a new observation but doesn't seem to be talked enough in literature.
December 5, 2024 at 9:44 PM
cseweb.ucsd.edu/~tzli/Score_...
I wrote down some random notes about the connection between score matching (aka diffusion models) and Stein's unbiased risk estimate (SURE). It shows why optimal denoising lead to optimal score. Not a new observation but doesn't seem to be talked enough in literature.
I wrote down some random notes about the connection between score matching (aka diffusion models) and Stein's unbiased risk estimate (SURE). It shows why optimal denoising lead to optimal score. Not a new observation but doesn't seem to be talked enough in literature.
Academics! Any tips for increasing class attendance/engagement apart from "gamifying" the participation (i.e., grading the participation)? My lecture attendance has been dropping (even though I personally think my lectures are okay), and it kind of hurt my motivation, so any advice is helpful.
December 3, 2024 at 10:53 PM
Academics! Any tips for increasing class attendance/engagement apart from "gamifying" the participation (i.e., grading the participation)? My lecture attendance has been dropping (even though I personally think my lectures are okay), and it kind of hurt my motivation, so any advice is helpful.
Reposted by Tzu-Mao Li
Come catch our BOF at SIGGRAPH Asia today! Learn more about the open source Slang initiative from NVIDIA that is now a part of the Khronos Group family!
Learn more: www.khronos.org/events/siggr...
#slang #shading #language #compiler
Learn more: www.khronos.org/events/siggr...
#slang #shading #language #compiler
December 3, 2024 at 9:31 PM
Come catch our BOF at SIGGRAPH Asia today! Learn more about the open source Slang initiative from NVIDIA that is now a part of the Khronos Group family!
Learn more: www.khronos.org/events/siggr...
#slang #shading #language #compiler
Learn more: www.khronos.org/events/siggr...
#slang #shading #language #compiler
Reposted by Tzu-Mao Li
Graphics has long studied how to make:
(1) realistic images 📷
(2) non-photorealistic images ✍️
(3) realistic sounds 🎤
What about (4) "non-phono-realistic" sounds?
What could that even mean?
Next week at SIGGRAPH Asia, MIT undergrad Matt Caren will present our proposal… 🧵
arxiv.org/abs/2409.13507
(1) realistic images 📷
(2) non-photorealistic images ✍️
(3) realistic sounds 🎤
What about (4) "non-phono-realistic" sounds?
What could that even mean?
Next week at SIGGRAPH Asia, MIT undergrad Matt Caren will present our proposal… 🧵
arxiv.org/abs/2409.13507
November 30, 2024 at 8:29 PM
Graphics has long studied how to make:
(1) realistic images 📷
(2) non-photorealistic images ✍️
(3) realistic sounds 🎤
What about (4) "non-phono-realistic" sounds?
What could that even mean?
Next week at SIGGRAPH Asia, MIT undergrad Matt Caren will present our proposal… 🧵
arxiv.org/abs/2409.13507
(1) realistic images 📷
(2) non-photorealistic images ✍️
(3) realistic sounds 🎤
What about (4) "non-phono-realistic" sounds?
What could that even mean?
Next week at SIGGRAPH Asia, MIT undergrad Matt Caren will present our proposal… 🧵
arxiv.org/abs/2409.13507
Reposted by Tzu-Mao Li
Our group at Google DeepMind is now accepting intern applications for summer 2025. Attached is the official "call for interns" email; the links and email aliases that got lost in the screenshot are below.
November 25, 2024 at 9:55 PM
Our group at Google DeepMind is now accepting intern applications for summer 2025. Attached is the official "call for interns" email; the links and email aliases that got lost in the screenshot are below.
Reposted by Tzu-Mao Li
Please share: Our lab is looking for new PhD students starting 2025!
If you are interested in research in geometry, computational design and digital fabrication, join us at EPFL!
More info on the lab: epfl.ch/labs/gcm/
More info on how to apply: www.epfl.ch/education/ph...
If you are interested in research in geometry, computational design and digital fabrication, join us at EPFL!
More info on the lab: epfl.ch/labs/gcm/
More info on how to apply: www.epfl.ch/education/ph...
Geometric Computing Laboratory
Our research aims at empowering creators. We develop efficient simulation and optimization algorithms to build computational design methodologies for advanced material systems and digital fabrication ...
epfl.ch
November 25, 2024 at 1:11 PM
Please share: Our lab is looking for new PhD students starting 2025!
If you are interested in research in geometry, computational design and digital fabrication, join us at EPFL!
More info on the lab: epfl.ch/labs/gcm/
More info on how to apply: www.epfl.ch/education/ph...
If you are interested in research in geometry, computational design and digital fabrication, join us at EPFL!
More info on the lab: epfl.ch/labs/gcm/
More info on how to apply: www.epfl.ch/education/ph...
Reposted by Tzu-Mao Li
My team RGL is looking for new PhD students starting 2025. If you are excited about topics like inverse rendering, compilers for graphics, and physically based modeling then please join us at EPFL. Info about the lab & admission process: rgl.epfl.ch/pages/jobs (Deadline: Dec 15)
November 22, 2024 at 3:14 PM
My team RGL is looking for new PhD students starting 2025. If you are excited about topics like inverse rendering, compilers for graphics, and physically based modeling then please join us at EPFL. Info about the lab & admission process: rgl.epfl.ch/pages/jobs (Deadline: Dec 15)
Reposted by Tzu-Mao Li
Khronos will oversee the open-source Slang shading language and compiler www.khronos.org/news/press/k...
This is big. Slang is cross-platform, backward-compatible, and trivial to port to. It supports differentiation/gradient computation as the first-class citizen, allowing to merge ML and graphics.
This is big. Slang is cross-platform, backward-compatible, and trivial to port to. It supports differentiation/gradient computation as the first-class citizen, allowing to merge ML and graphics.
Khronos Group Launches Slang Initiative, Hosting Open Source Compiler Contributed by NVIDIA
The Khronos Group has announced the launch of the new Slang™…
www.khronos.org
November 21, 2024 at 4:19 PM
Khronos will oversee the open-source Slang shading language and compiler www.khronos.org/news/press/k...
This is big. Slang is cross-platform, backward-compatible, and trivial to port to. It supports differentiation/gradient computation as the first-class citizen, allowing to merge ML and graphics.
This is big. Slang is cross-platform, backward-compatible, and trivial to port to. It supports differentiation/gradient computation as the first-class citizen, allowing to merge ML and graphics.
Hi! I'll share classical and less known graphics (and other) papers here. The first paper I'll share is "Model-Based 3D Hand Pose Estimation from Monocular Video" from de la Gorce et al. in 2011. They proposed one of the first differentiable rasterizers that can properly handle edge discontinuities.
November 20, 2024 at 6:31 PM
Hi! I'll share classical and less known graphics (and other) papers here. The first paper I'll share is "Model-Based 3D Hand Pose Estimation from Monocular Video" from de la Gorce et al. in 2011. They proposed one of the first differentiable rasterizers that can properly handle edge discontinuities.