Georgia Tech Prof; Tsinghua, Caltech, NYU Courant * (diffusion) generative model, probabilistic ML * AI4Science * deep learning theory * applied & comput. math
Joined October 2021
- Tweets496
- Following224
- Followers2.2K
- Likes2.6K
Pinned Tweet
Does GenAI create new knowledge? arxiv.org/abs/2602.06021 gives
* 1st explicit characterization of diffusion model's generalization
* more precise than offered by classical stat. learning theory
* systematic integration of various inductive biases (training+architecture+inference)
Molei Tao retweeted
Brute force computation is not enough for intelligence. Clever new methods are needed. The science of AI is far from finished. IMHO
Molei Tao retweeted
Introducing FrontierPhysics - a benchmark evaluating agents for end-to-end physics research
Our core team from physics labs at Berkeley, Caltech, and Harvard recruited 42 physicists from 26 institutions. 28 of them published papers on Nature, Nature Physics, PRX, PRA*
1/7 🧵
Molei Tao retweeted
just 10 days left to apply: Flatiron Research Fellowship in the Center for Computational Mathematics! 2-3 years postdoctoral support for independently-led research at the Simons Foundation Flatiron Institute in NYC- join us!
apply.interfolio.com/193799
simonsfoundation.org/flatiro…
ALT molecular or atomic landscape with abstract electron/photon/atom-like objects in the landscape
Molei Tao retweeted
We post job opportunities in industry and academia in our @diffusion_llms discord.
@GeorgiaTech 's Dynamical ML Group is hiring PhDs and Postdocs in diffusion LLMs
cc: @MoleiTaoMath
Join our discord: discord.gg/CuPnEMtfJ
Georgia Tech Dynamical ML Group is recruiting PhD students and postdoc in diffusion language models for Fall 2027
Please join our discord server to learn more.
discord.gg/CuPnEMtfJ
Want faster language model inference? MDraft trains diffusion drafters with multi-draft on-policy distillation, boosting accepted draft lengths for more efficient speculative decoding!
Molei Tao retweeted
I know many PhD students are questioning what their paths mean as AI accelerates scientific discovery. That anxiety deserves to be taken seriously.
I wrote some reflections in a recent blog post. My students found them helpful, so I’m sharing them more widely.
I hope it offers a little light as we navigate this strange time. Please share it with someone who might need it.
pages.cs.wisc.edu/~sharonli/…
Molei Tao retweeted
I've posted some slides on my website outlining OpenAI's approach to disproving the exponential time hypothesis: msellke.com/Files/ETH-False-…
The outline skips some steps, so it gains a smaller power of log(n) in the exponent than the fully optimized algorithm.
Molei Tao retweeted
Tired of waiting for your diffusion models?
🚢 We just shipped a major FastGen update:
- new models: H3, LTX-2.5, LingBot-World, Cosmos 3, FLUX.2
- new methods: PDD, AYF, AnyFlow, Causal Forcing
- new features: multimodal distillation, image editing, camera conditioning, KV cache management, ComfyUI
🔗 Try it out here: github.com/NVlabs/fastgen
Molei Tao retweeted
Generating proteins -> ??? -> Testing them in the lab
The missing piece is SELECTBENCH – evaluating your generations before sending them to the lab
- We design metrics to evaluate your model on the selectivity task
- We collect three datasets of ON/OFF targets from different sources and of different difficulty levels
- We study how modern generative models perform on these tasks (far from perfect)
- With SELECTBENCH, the question of generating proteins becomes the question of the throughput of your model!
- Check it out at #neurips2026 and benchmark your model using the code from github.com/lovetaro/selectbe…
This is one of the links in our long chain of works on generating selective proteins (see my slides for the synthesis docs.google.com/presentation…)
A molecule can bind the right protein and still be the wrong drug. Why? Because it might also bind proteins we don't want it to, potentially causing serious side effects.
📄 Paper: arxiv.org/abs/2610.24124
Molei Tao retweeted
Please apply. No teaching, complete freedom! You can work with any faculty!
UC Berkeley Department of Statistics is hiring! We’re seeking applications for our Postdoctoral Neyman Fellow position.
Details & apply: aprecruit.berkeley.edu/JPF05…
#Statistics #Probability #DataScience #FacultyJobs #UCBerkeley
Molei Tao retweeted
Parallel Decoding Distillation (PDD) is taking off 🛫
We’ve only released PDD end of July and it’s already adopted in:
- Alibaba’s MiniMax H3: huggingface.co/alibaba-pai/M…
- WorldPlay2’s causal distillation: worldplay2.github.io/
- FastVideo’s FastH3 Omni: haoailab.com/blogs/fastvideo…
- NVIDIA’s large language continuous diffusion model: arxiv.org/pdf/2610.02665
- Amazon’s generative forecasting model: arxiv.org/abs/2610.22358
- NVIDIA’s & MSR’s extensions to parametric student trajectories: alan-lanfeng.github.io/PTD & arxiv.org/pdf/2610.18472
We’ll be open-sourcing our implementation soon - stay tuned!
Having worked with many distillation methods for accelerating diffusion & flow models, I’m still blown away by the simplicity of Parallel Decoding Distillation (PDD).
1️⃣ State-of-the-art quality and diversity with variable NFE
2️⃣ First to scale trajectory-distillation to few-step video generation
PDD is about as cheap and simple as it gets:
🎯single, regression-based MSE loss using 1 student & 1 detached teacher forward
❌NO data required
❌NO adversarial loss or alternating training
❌NO JVP or finite-difference approx.
❌NO additional time-embedding or trainable models (e.g. fake score, discriminator)
❌NO stabilization tricks (e.g. normalization, clipping, warm-up)
Molei Tao retweeted
Join @FlatironInst @SimonsFdn as a Research Fellow in NYC 🚀 Lead cutting-edge work in computational science & ML with top collaborators. Apply by Nov 15: apply.interfolio.com/193799
More on ML@CCM 👉 users.flatironinstitute.org/…
Keen to work with folks in #AIforScience & #GenerativeAI
Molei Tao retweeted
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
Molei Tao retweeted
RFDiffusion or Proteina? You don't want to miss this one 🔥🧬
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
Molei Tao retweeted
🚀 Today at GTC Berlin we introduced RFD4-Proteina! A close one-year collaboration between GenAIR and David Baker's group at @UWproteindesign !
🧬 Design proteins faster and send fewer, better candidates to the lab.
Introducing RFD4-Proteina, a new NVIDIA BioNeMo open model co-developed with @UWproteindesign.
▫️Fast: 13× faster generation than RFdiffusion3 at 200 residues
▫️ Smart: state-of-the-art across 12+ protein design tasks
▫️ Programmable: set your design inputs and use test-time compute on harder problems
Start with our binder-design tutorial nvda.ws/3VK9Uvr
Molei Tao retweeted
Check out RVM: simple, effective RL fine-tuning for diffusion models ⚡
Roll out (no grads) → compute rewards → re-noise → reward-weighted velocity regression + anchoring
Unifies previous approaches and scales to video models with SOTA performance!
Molei Tao retweeted
Exciting to see the community building on FastGen and pushing distillation techniques forward! 🚀
This cool new work builds on ideas from our PDD and PiFlow, exploring novel parameterizations of student heads. Great to see these ideas evolving!
Excited to introduce Simplified Matching Distillation (SMD) for few-step diffusion🧵
No auxiliary score model. No adversarial training. No generator modification.
You will get:
• Photorealistic appearance
• High-quality dynamics
• Memory-efficient training
• Mode covering with diverse outputs
SMD works well across images, video, joint audio–video, and 3D gen, validated across model scales up to 33B parameters.
Besides, SMD supports:
- Multi-teacher capability merging (like OPD in LLM)
- Cross-model capability transfer
- Bidirectional teacher to causal distillation
Full release. Paper, code, model and data.
Project Page: zjwfufu.github.io/SMD-Page/
Paper: arxiv.org/abs/2610.18472
Code: github.com/zjwfufu/SMD
Model Card & Data: huggingface.co/zjwfufu/SMD
Demo Video 👇
Molei Tao retweeted
1/4 Today, we’re releasing Mercury 3. Mercury 3 is by far our most powerful model and the most intelligent diffusion LLM ever released. It outperforms GPT-6 Luna and Haiku 5.5 on quality while running at 1000+ tok/sec.
🤖 Made with AI
Molei Tao retweeted
A nice presentation by @paveltyletski on
Diffusion Gemma: 4x faster text generation.
I think that text diffusion will not only be 4x faster and 10x more energy efficient, but eventually it will also be of higher quality, and supersede autoregressive LLMs.
youtu.be/3n5RN7i8h2Y?si=YkYz… via @YouTube
Molei Tao retweeted
I recently moved to TU Darmstadt (Germany) and am currently hiring PhD student through ELISS.
ellis.eu/news/ellis-phd-prog…
If you interested, please apply and choose me as a potential advisor. Topics include Continual/Distributed/Federated/Active/Transparent AI.