We build biomolecular foundation models to enable new science. SeedFold & SeedProteo.
Shanghai
Joined January 2026
- Tweets21
- Following107
- Followers300
- Likes14
Here is SeedProteo, our latest diffusion-based model for de novo all-atom protein design from ByteDance Seed! Our server is now live — feel free to give it a try! seedfold.io/dashboard/protei…
Insights 🧐 Moving beyond conventional understanding:
🎯 Automatic control over secondary structure, unlocking novel binder conformations
💡 MRF Decoding outperforms traditional coordinate decoding.
🔬 Co-design is key for tackling complex targets.
🙎 Team Member
Led by Wei Qu (@qu0518), with key contributions from Yiming Ma (@Yimima_), Fei Ye (@FeiYE00844289), Chan Lu (@BlingBl83745470), Yi Zhou (@dugu9sword), Kexin Zhang (@WingsofPlatinum), Lan Wang (@caroline88688), Minrui Gui (@Gui39194Gui) and our team lead Quanquan Gu (@QuanquanGu).
congrats the team @IsomorphicLabs on the incredible work!
The drug design engine we’re building at @IsomorphicLabs is extending the SOTA further across key benchmarks, showing huge progress in accuracy and capabilities critical for in-silico drug discovery. Incredible work from @maxjaderberg and the entire team at Isomorphic Labs!
SeedFold retweeted
I think GEM has been the most interesting BioML workshop every year💙
- and I'm pretty pumped to attend hopefully submit and find this sort of workshop (eg. building the bridge to experimental biology) such a good fit for ML conferences b/c its not usual!
Hi network! We're excited to invite all of you for the GEM Workshop at ICLR 2026 (back for the third time!) in Rio de Janeiro this April! 🇧🇷
Ever year at @iclr_conf, the @gembioworkshop brings together very best AI researchers and experimentalists together to tackle real biological/biochemical challenges -- I equate it to the warm home of the AIxBio community! 🏡 We’d love to see your work there! 🧑💻 🧑🔬
We also have some amazing speakers (the current/future leaders of biotech): @chorye (bioautomation @DukeU), @MargauxPinney (high-throughput data gen @UCBerkeley), Octávio Franco (antimicrobials @UCDBoficial), @BenKompa (scientific superintelligence @LilaSciences), and @QuanquanGu (AI4Bio @BytedanceTalk)!! 🤩
Why you should submit:
✨ Two Tracks: Dry-lab (Generative ML advancements) and Wet-lab (Experimental results & high-throughput methods).
📜 Journal Partnership: Selected papers will be considered for fast-track review @NatureBiotech!
🌱 Seed Grants: We’re offering $1,000 grants to catalyze new dry-lab/wet-lab collaborations formed at the workshop.
🌍 Support: Travel grants are available for students from underrepresented communities.
🔬 Design Competition: Opportunity to make designs to RBX1, an E3 ligase, and have them tested @adaptyvbio! See website for details: gembio.ai/gemadaptyv2026
📅 Submission Deadline: 5th February 2026, 11:59 PM (Anytime on Earth): openreview.net/group?id=ICLR…
👉 Learn more here: gembio.ai/
SeedFold retweeted
Tomorrow in the reading group we discuss "SeedFold: Scaling Biomolecular Structure Prediction" arxiv.org/abs/2512.24354
Outperforming AF3 on multiple tasks a little bit.
Join us on zoom at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/stark…
Introducing SeedFold from ByteDance Seed, a biomolecular structure prediction model that outperforms AlphaFold3 on protein-related folding tasks. seedfold.github.io/
🙎 Team Member
Led by Yi Zhou (@dugu9sword ) & Chan Lu (@BlingBl83745470 ), with key contributions from Yiming Ma (@Yimima_ ), Wei Qu (@qu0518 ), Fei Ye (@FeiYE00844289 ), Kexin Zhang (@WingsofPlatinum ), Lan Wang (@caroline88688 ), Minrui Gui (@Gui39194Gui ), and our team lead Quanquan Gu (@QuanquanGu ).