
Research Scientist @NVIDIA | PhD @Mila_Quebec, BS @FudanUniversity | Deep Generative Learning | Proteins and Molecules. Views are my own.
Santa Clara, California, USA
Joined September 2021
- Tweets223
- Following1.2K
- Followers1K
- Likes3K
Pinned Tweet
Our latest progress on binder design is here, now backed by massive-scale wet-lab validation! 🧬 Proud to contribute to this amazing team pushing the boundaries of what’s possible.
📢📢 Proteina-Complexa 📢📢
Atomistic Binder Design with Generative Pretraining and Test-Time Compute + Experimental Validation at Scale
⭐️ Project page (research.nvidia.com/labs/gen…) for:
📜 Method paper (ICLR 2026 Oral)
🧬 Wet lab paper
🛠️ Code & models
📁 Data
🧵 Thread
(1/n)
1
24
2,813
Zuobai Zhang retweeted
I promised more on TMol in the RFD4-Proteina thread. Now with the paper on arxiv here we go! 🧵
Rosetta-style all-atom energies, GPU batching, and gradients in PyTorch. A way to put molecular energetics directly into your model, combining deep learning with physics. 1/n
Zuobai Zhang retweeted
Thanks to the thousands of you that used the RFD4-Proteina online GUI and gave feedback! Thanks to the one and only @sokrypton it is now even easier to use, both on HF and on your own laptop/tablet/even phone! Make your own pesticide degrader like legend @SethWoodbury1 in our paper, including refolding! Links etc in 🧵
Zuobai Zhang retweeted
Claude was trained on protein sequences, at scale.
We gave 20 language models the start of little-studied bacterial proteins and asked for the next amino acids. Only the latest Claude models predict them. Not GPT, not Gemini, not seven open-weight models.
Zuobai Zhang retweeted
🎉 Exciting Nemotron-Labs-Sigma release! Continuous diffusion opens up exciting possibilities for fast, controllable language generation through distillation and steering. Congrats to the team!
All weights released and available!
See @MardaniMorteza's thread below for details.
📣 NVIDIA is releasing a collection of open model weights: Nemotron-Labs-Sigma — 14 checkpoints at 3B/8B.
Language models have stayed discrete. We bring continuous diffusion to language as in vision.
Smooth ODE trajectories (16-D) unlock distillation and steering: 8 TPFs for math, 4 TPFs for code, with accuracy and diversity preserved. 🧵 1/
Zuobai Zhang retweeted
🔥⚛️ The molecular simulation ecosystem just got accelerated 3x ⚛️🔥
Faster, better molecular simulations
=
more routine use in new scientific use cases
=
more confident, more accurate wet lab experiments
xitter.gq/NVIDIAHealth/status/21…
🆕 cuPotential
A CUDA-X library for computing nonbonded interactions in molecular dynamics. The OpenMM plugin replaces the nonbonded force, integrator, and barostat.
In NPT benchmarks on systems from 24K to 400K atoms, it ran over 3x faster than OpenMM on RTX PRO 6000 Blackwell and about 2x faster on B200, H100, A100, L40S, A10, L4, and T4.
Accuracy holds up too, with a few hundred times less energy drift than default PME.
💻 Github nvda.ws/3WIwogJ
📄 Technical Blog nvda.ws/4AyIpDX
📍 Find us at #SC26 👇
We have done a major update on distillation and speculative decoding, and release our Nemotron-Labs-Sigma model family on Huggingface. Check it out at huggingface.co/collections/n…
Kudos to all collaborators and looking forward to the future of continuous diffusion LLMs!
📣 NVIDIA is releasing a collection of open model weights: Nemotron-Labs-Sigma — 14 checkpoints at 3B/8B.
Language models have stayed discrete. We bring continuous diffusion to language as in vision.
Smooth ODE trajectories (16-D) unlock distillation and steering: 8 TPFs for math, 4 TPFs for code, with accuracy and diversity preserved. 🧵 1/
Zuobai Zhang retweeted
We've released the 3B/8B checkpoints for Sigma on HuggingFace 🤗!
huggingface.co/collections/n…
💫 Large Language Continuous Diffusion Models
Presenting Sigma, the first large-scale (3B/8B) continuous diffusion LM (dLM) trained with likelihood.
📈 Comparable with discrete dLMs and AR on math and coding
🎛️ Enables meaningful study of inference-time interventions
Jointly led with Wei Guo (@WeiGuo01), Jean-Marie Lemercier (@jm_lemercier), Simon Welker (@_cobalamin)
Team: @YongganFu @mmkamani7 Sajad Norouzi @julberner @tomasgeffner @karsten_kreis @YongxinChen1 @MoleiTaoMath @jwthickstun @PavloMolchanov Ante Jukic @ArashVahdat @MardaniMorteza
Zuobai Zhang retweeted
📣 NVIDIA is releasing a collection of open model weights: Nemotron-Labs-Sigma — 14 checkpoints at 3B/8B.
Language models have stayed discrete. We bring continuous diffusion to language as in vision.
Smooth ODE trajectories (16-D) unlock distillation and steering: 8 TPFs for math, 4 TPFs for code, with accuracy and diversity preserved. 🧵 1/
Zuobai Zhang retweeted
Big update to our Nemotron-Labs-Sigma!
⚡ Strong distillation results with just 4 sampling steps
🔥 3.5× faster speculative decoding
🔓 All checkpoints and code released!
📣 NVIDIA is releasing a collection of open model weights: Nemotron-Labs-Sigma — 14 checkpoints at 3B/8B.
Language models have stayed discrete. We bring continuous diffusion to language as in vision.
Smooth ODE trajectories (16-D) unlock distillation and steering: 8 TPFs for math, 4 TPFs for code, with accuracy and diversity preserved. 🧵 1/
Zuobai Zhang retweeted
What a strange week for @JensenHuang and @nvidia. It all feels orchestrated and targeted, and I hope we get to the bottom of it.
I’ve been at NVIDIA for 12.5 years, started as an intern and made it to Research Director thanks to incredible colleagues and especially Research management and Jensen. The journey I’ve witnessed has been fascinating. 🧵
Zuobai Zhang retweeted
🧬 We’re hiring at the NVIDIA × Lilly AI lab—across both companies!
Help build the next generation of drug discovery, bringing AI, robotics and experimental science together in our joint Bay Area lab.
#Hiring #AIforScience #DrugDiscovery
Zuobai Zhang retweeted
🚀 Excited to share BindClaw! 🦀
Starting from a prompt or research paper, BindClaw connects biological mechanisms to protein design: identify targets and binding sites → build mechanism-specific computational assays → generate and assess binders → refine designs using the results.
We use agents to evaluate whether designs fit the intended biological objective, including competition with a native partner and preference for a particular molecular state. 🧬
In a human-guided calmodulin campaign, 15 of 18 designs showed binding to calcium-loaded CaM, including subnanomolar binders supported by both BLI and SPR.
This work is an incredible team effort together with @DidiKieran , @saint__ai, @ Kyle Gion and @sacdallago and many others!
📄paper/project: research.nvidia.com/labs/dbr…
💻code: will be released in a few weeks!
Zuobai Zhang retweeted
As usual, stellar work by my colleagues, @julberner, Chao Liu, @amsabour , @ArashVahdat! 🔥
FastGan can accelerate any diffusion model! 🚀
The release also includes, finally, our "Align Your Flow" flow map code and weights, huggingface.co/nvidia/FastGe…, following popular demand! 🛠️
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
Zuobai Zhang retweeted
RFD4-Proteina on HuggingFace, both in Diffusers and interactive spaces to work with, try it out and let us know what you think!
Zuobai Zhang 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
Hi! We just released Mol-1, the frontier open-source cofolding. Try and benchmark it for your research and real-world problems: built for science, agents, and workflows.
Sign-up and cook. lab.molence.com
Open-sourced for all: github.com/molence/Mol-1
you're gonna like it
Introducing Mol-1: Open Frontier Biomolecular Intelligence 🚀🚀🚀
📊 75.0% on FoldBench-AB, near IsoDDE's reported 75.58%!!!
🧬 60k-token assemblies on one single H20, outperforming Anthropic 8/10.
🎯 VHHs binding hit rate as high as 63% with best SPR KD at 43 pM.
GitHub: github.com/molence/Mol-1
Try it: lab.molence.com
Zuobai Zhang retweeted
📢 RFD4-Proteina talks 📢
Great seeing @kpowgerade introduce RFD4-Proteina at @nvidia GTC Berlin, and fun presenting it with @nscorley at the GTC Biopharma summit!
Next up: our own little Eurotour - with guest appearances from David himself in the UK. Come by if you’re around! 🧵 1/3
Zuobai Zhang retweeted
🚀 Are you a PhD student pushing the boundaries of AI, robotics, graphics, or accelerated computing?
NVIDIA's Graduate Fellowship offers up to $60K in funding, mentorship from NVIDIA researchers, and a summer research internship!
⏳ Apply by October 30!
blogs.nvidia.com/blog/applic…
Zuobai Zhang 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
Kieran is a beast 🔥 Go check out RFD4-Proteina!
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



























