-
Tweets134
-
Followers115
-
Following501
-
Likes211
Now coming to a #NeurIPS2026 near you as a Spotlight 🔦!
Protein–ligand cofolding models are getting incredibly powerful… but do they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and
@gavincrooks @phinance99 What about having papers stored as 1024 dimensional latent vectors
It’s getting hard to keep track of all the new open-source cofolding models coming out. To help everyone stay up to date, I'm excited to share cofoldarena.ai, a PDB-synced leaderboard of open models, updated weekly. All predictions are available to view & download! (1/4)
Small model, looooong context Reverso is now improved to handle significantly longer contexts, up to 16k! We pretrain our foundation model to handle inputs at multiple frequency scales, and observe an improvement in forecasting performance while maintaining fewer than 3M params
We're presenting DeCAF ☕️: A few-step cofolding model with all-atom flow maps at the GenBio workshop at #ICML2026 as a Spotlight in the morning poster session!! Also, we've now released the code and checkpoints from the paper: code🧑💻: github.com/genesistherape… paper🔗: arxiv.org/abs/2606.08375 Come by and say hi 👋!
Protein–ligand cofolding models are getting incredibly powerful… but do they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and
Hi everyone! I’ve moved to the Bay Area for a summer research internship at @nvidia. Beyond exciting work, I'd love to meet new people doing exciting stuff (incl. stuff I don't work on myself rn!). If you’re around, I’d love to connect! Even if just for a jam session!
Big news from Boltz - our biggest update yet! 🚀 Today we’re releasing two new state-of-the-art models for protein and small molecule design with extensive wet lab validation and a new API to run all of our models on scalable GPUs wherever you (or your agents) work! 🔥
extremely excited about this work bringing flow maps to cofolding -- check it out! by using flow maps, we not only have faster inference, but we obtain access to more powerful reward guidance & search techniques. these leverage an exact reward computation provided by the flow map, which is significantly more precise than more standard denoiser-based estimates
Protein–ligand cofolding models are getting incredibly powerful… but do they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and
DeCAF is our first method for accurate distillation of all-atom cofolding diffusion models into fast flow maps. this can unlock a lot of practical applications of powerful models like Pearl, e.g., scalable synthetic data generation. very proud of this work, congrats to the team!
Protein–ligand cofolding models are getting incredibly powerful… but do they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and
Protein–ligand cofolding models are getting incredibly powerful… but do they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and 20x faster than Boltz 1x. ⚡🧵 📜 Blog: genesis.ml/news/genesis-m… 🔗arXiv: arxiv.org/abs/2606.08375 Code (coming soon): github.com/genesistherape…
We got 2 big birds with one stone: 1) DeCAF-Pearl makes all-atom cofolding much faster than previously possible and 2) enables inference time search.⚡️ An incredible amount of work was done by a very talented team, and it was a pleasure to participate:)
Protein–ligand cofolding models are getting incredibly powerful… but do they have to be so slow? 🧬🐢💊 Our new preprint introduces a new flow-map framework called DeCAF for fast few-step cofolding — up to 5× faster while preserving sample quality on the SOTA Pearl model and
Our Equivariant Deep Learning book is finally available for purchase as hardcover 📖 and it immediately became a bestseller 🚀 worldscientific.com/worldscibooks/…
🚀 New Bestselling Book! The future of Geometric Deep Learning is here! Master Equivariant and Coordinate Independent Convolutional Networks through the groundbreaking Gauge Field Theory of Neural Networks. Build dramatically more data-efficient, robust, and powerful models.
Very excited about this work! Language modeling via flow maps allows us to rethink how to build language models that do latent reasoning and fast generation! Glad to play my small part in a wonderful effort with @PPotaptchik, @json_yim, @adhisarav, Eric Vanden-Eijnden, @msalbergo!
New paper! Presenting Discrete Flow Maps: paper: arxiv.org/abs/2604.09784 blog: malbergo.me/discrete-flow-… A laughable problem for me these days is that @nmboffi and I share a research brain, and we have had, time and again, a conversation that ends with “ha so I guess we’re
Arriving in Rio 🇧🇷for #ICLR! I will present GLASS Flows + Diamond Maps in the coming days - starting today with GLASS Flows Oral at 11:30 AM! I am looking forward to meeting new people! Feel free to reach out! 1/3
We release Diamond Maps💎 unlocking accurate and efficient guidance for diffusion models. Our experiments show that our methods scale incredibly well. Excited to see what people will build with this! Accurate guidance has been a notoriously hard problem, but in this work, we’re
@andrewgwils I'm sad to admit, this might not even be possible for me.
We are also releasing self-contained lecture notes that explain flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI. 📖 Read the notes here: arxiv.org/abs/2506.02070 Joint work with @EErives40101.
🚀MIT Flow Matching and Diffusion Lecture 2026 Released (diffusion.csail.mit.edu)! We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include: 📺 Videos:
Recordings have just dropped on YouTube! You should definitely check out this amazing resource if you want to learn about flow matching. Peter is the best of the best and he put so much effort into this. It was a pleasure to contribute my small part:)
🚀MIT Flow Matching and Diffusion Lecture 2026 Released (diffusion.csail.mit.edu)! We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include: 📺 Videos:
@andrewgwils I started as a chemist. Took a long detour in "pure" AI for a while. Now I partake in the so called "AI4Science" party. Am I a scientist? Or an ML researcher? I wouldn't know. I'm probably neither. But I certainly enjoy both.
Matěj Kripner @MatejKripner
654 Followers 883 Following applied RL in robotics, vision, and automated theorem proving; advised by @straka_milan and @lifrordi; currently at Google Zürich
Luca Eyring @LucaEyring
698 Followers 1K Following Student Researcher @GoogleDeepmind, PhD Student @TU_Muenchen, previously Research Intern @InceptiveCom
Khoa Tuan Nguyen @Khoa_NguyenTuan
928 Followers 7K Following Enjoy learning new things. PhD student at Ghent University Global Campus in Korea.
Ollie Perrée @OPerree
3 Followers 658 Following
Nhat Tran @nhat_416
0 Followers 2K Following
Karthik Kalyani @KarthikKal25328
10 Followers 2K Following
Asad Ansari @a5adansari
7 Followers 4K Following
Indra Yudhistira @indrayudhistira
36 Followers 4K Following
em @emb5o1
0 Followers 2K Following
Rodrigo G. del Cueto @rdelcueto
115 Followers 1K Following Computer scientist exploring the world through code, photography, and science. Firmware engineer, cyclist, and lifelong learner.
Ranga Reddy @irangareddy
592 Followers 2K Following tuning agents to build software. 2x apple ssc winner. sih ‘19 finalist.
Vaibhav Wanere @vbwanere
282 Followers 7K Following Do your part and get out of the way.... Process Automation @CaterpillarInc | Robotics @Penn | Curious Creative Critical |
Jai Pise @JaiPise1
19 Followers 1K Following
roshnipoudel @RoshniPoude1
5 Followers 628 Following
Sayak @sayak38kolay
371 Followers 6K Following Statistics student. Interested in Math, Python, R, Machine Learning, History, and Economics. Lover of all things stochastic ❤️. RTs not necessarily endorsements
Ez Wind @ez_wind
72 Followers 5K Following
David Alvarez Melis @elmelis
2K Followers 2K Following Asst. Prof. @hseas @KempnerInst || Researcher @MSRNE || ML + NLP || Previously: @MIT_CSAIL NYU @IBMResearch @ITAM_mx
RISHI KUMAR @rishikumar_17
47 Followers 3K Following
Gilad @giladturok
1K Followers 5K Following Machine learning PhD student @cornell | diffusion language models | Prev: @Uber, @FlatironInst, @Columbia
Kshitiz Khanal @kshitizkhanal7
2K Followers 5K Following Applied ML research for energy and transportation. Here for football banter and keeping tabs on AI
Charbel Beaini @cb_dotcom
5 Followers 395 Following
Rakib Islam @jahin114
175 Followers 936 Following
Anar Rzayev @AnarSnowball
458 Followers 2K Following Cooking proteins with ML @ ISTA 🇦🇹 Ex-Research student @ KAIST 🇰🇷 | Prev CS & MATH @ EPFL 🇨🇭 | Bronze medals @ IMO 2017, 2019 🇧🇷 🇬🇧
Shota Natenadze @shotanat
294 Followers 3K Following AI Technical Lead @provectus_inc, passionate about machine learning, LLMs, and advancements in AI technology.
1984 @hervie_kofi
468 Followers 6K Following
Sneh Sourabh @sneh_sourabh_
7 Followers 2K Following
Kartik @ayyar
2K Followers 2K Following Engingeering lead for @Roblox Assistant. Past: Smart Reply @GoogleAI, cofounder LetterFeed (exit: @Google), @utcompsci. Opinions not my employers.
Ashwin Vaswani @ashwin_vaswani
2K Followers 7K Following Research Scientist @GoogleDeepMind | Prev: @CarnegieMellon | @GoogleIndia | APPCAIR, @BITSPilaniGoa | @qtimlab, Harvard
Binh @pham_blnh
4K Followers 1K Following breaking robots @livekit ↝ prev fellow @shipfr8 and @southpkcommons
Davood Soleymanzadeh @davoodsz
84 Followers 1K Following Ph.D. Student @TAMU; Robotics; Motion Planning; HRC
Pedro Henrique @pedroh2993
14 Followers 4K Following
Shurik Shapiro @ShapiroShu6992
32 Followers 2K Following
John D. Pope 🦒 @johndpope
2K Followers 7K Following Hi-Yo, Silver! - prepare for financial reset. 🧙♂️🔮 🍿 I built a chrome extension for grok imagine -
Sirak Ghebremusse @sirakzg
820 Followers 7K Following Director of Machine Learning at Brahma AI , ex @OTOY and @ILMVFX
Barak Hirshberg @barak_hirshberg
2K Followers 1K Following #MolecularSimulations | Associate Professor @TelAvivUni 🇮🇱 | PD: Rothschild Fellow @GroupParrinello @ETH_en 🇨🇭 | PhD: Adams Fellow, w/Benny Gerber @HebrewU
Liam Fedus @LiamFedus
41K Followers 1K Following Building industrial-scale science at @periodiclabs Past: VP of Post-Training @OpenAI; Google Brain
alex peysakhovich @alex_peys
6K Followers 845 Following partner @shv, ex-facebook ai research. currently really into ai for biology. building models with our port cos.
Juno Nam @junonam_
325 Followers 361 Following ML + atomistic simulations | PhD student at @MIT_DMSE | @RGBLabMIT
Maxence Noble @maxence_noble
262 Followers 157 Following Postdoctoral Researcher @ CFM ML Lab | ML PhD @Polytechnique
achira-ai @achira_ai
283 Followers 0 Following Achira is building atomistic foundation simulation models to power the future of drug discovery.
Ben Blaiszik @BenBlaiszik
5K Followers 3K Following Making the world a little better with software, materials, and community. Group Leader - AI & data infrastructure at @uchicago/@argonne. Opinions are mine.
Paul Wollenhaupt @pwolle_
154 Followers 532 Following Modern Day Alchemy | Founding AI Research Scientist at @chaidiscovery
François Chollet @fchollet
733K Followers 829 Following Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
Discovery Loop @DiscoLoopAI
54K Followers 4 Following Automating discovery to accelerate science and engineering for the world.
Mark Goldstein @marikgoldstein
2K Followers 2K Following absolutely discontinuous with respect to Lebesgue measure. research fellow in ai for science ⚛️ @FlatironInst + ai safety fellow @AnthropicAI
Kairos Materials @KairosMaterials
71 Followers 3 Following Kairos Materials builds full-stack AI for new materials discovery, from AI foundation models, AI-native labs to industrialization. https://t.co/DEtjChNLbE
Phil Leung @proleu
1K Followers 621 Following cofounder @Xaira_Thera formerly @UWProteinDesign views my own https://t.co/4NqdzMfpiK
Gordon Research Confe... @GordonConf
20K Followers 180 Following An international forum for the presentation and discussion of scientific research at the frontiers of science.
Andrew Foong @AndrewFoongYK
2K Followers 257 Following AI for cancer care @MayoClinic - we’re hiring! Previous: @MSFTResearch, @GoogleDeepMind, @Cambridge_Uni
Guan-Horng Liu @guanhorng_liu
2K Followers 417 Following 👨💻 Research Scientist @MetaAI (FAIR/MSL) • I build generative models with scientific structures • 🎓 @GeorgiaTech @CarnegieMellon
Lorenz Richter @lorenz_richter
470 Followers 173 Following Researcher at @ZuseInstitute, founder of @dida_ML
D. E. Shaw Research @DEShawResearch
6K Followers 0 Following D. E. Shaw Research develops and uses paradigm-shifting computational technologies to reshape the process of drug discovery.
Killian Sheriff @KillianSheriff
698 Followers 3K Following ML for materials discovery @PeriodicLabs | I like metallic alloys.
Maruan Al-Shedivat @alshedivat
1K Followers 549 Following Building something new | Ex: @genesismolai, @OpenAI, @GoogleAI | PhD in ML from @CarnegieMellon (@mldcmu)
Joey Bose @bose_joey
5K Followers 292 Following Assistant Professor @imperialcollege and @Mila_Quebec Affiliate member. Into Geometry ⋃ Generative Models ⋃ AI4Science. Ex-@UniofOxford, @Mila_Quebec, @UofT.
Boris Kozinsky @bkoz37
996 Followers 97 Following
Nicholas Boffi @nmboffi
2K Followers 1K Following assistant professor @mldcmu & cmu mathematics. creating the future of generative modeling with flow maps previously @Harvard, @MIT, @GoogleAI, @NYU_Courant.
Arash Vahdat @ArashVahdat
11K Followers 927 Following Research Director, leading fundamental generative AI research (GenAIR) @nvidia research, occasionally volunteer at California Search & Rescue, views are my own.
Jacques Lucke @JacquesLucke
11K Followers 59 Following Blender developer, and more. Also on https://t.co/Vpb1WH9kF6
Luca Eyring @LucaEyring
698 Followers 1K Following Student Researcher @GoogleDeepmind, PhD Student @TU_Muenchen, previously Research Intern @InceptiveCom
Samuel Stanton @samuel_stanton_
3K Followers 1K Following technical staff @AnthropicAI | prev. cofounder @CoefficientBio | @NYUDataScience PhD | working on AI for scientific discovery
David Alvarez Melis @elmelis
2K Followers 2K Following Asst. Prof. @hseas @KempnerInst || Researcher @MSRNE || ML + NLP || Previously: @MIT_CSAIL NYU @IBMResearch @ITAM_mx
Gilad @giladturok
1K Followers 5K Following Machine learning PhD student @cornell | diffusion language models | Prev: @Uber, @FlatironInst, @Columbia
Brady Johnston @bradyajohnston
17K Followers 2K Following struc. biologist, scientific animator, creator of #MolecularNodes for #b3d he/him 🐘: [email protected] ⛅️ @bradyajohnston
Jan Jensen (janhjense... @janhjensen
9K Followers 597 Following Computational chemist at the University of Copenhagen. PChem Editor-in-Chief @PeerJChemistry. #compchem
Kresten Lindorff-Lars... @LindorffLarsen
15K Followers 2K Following Protein and coffee lover, father of two, professor of biophysics and sudo scientist at the #LinderstrømLang Centre for Protein Science 🇩🇰
Gabriel Rocklin @grocklin
3K Followers 608 Following High-throughput protein design and biophysics | Asst Prof, Northwestern Pharmacology @NuFeinbergMed @NUSynBio.
Tian Xie @xie_tian
5K Followers 514 Following Founding Member @ Prometheus; AI for materials; Previously Project Lead @ Microsoft Research, MIT, DeepMind, Google X; MIT TR35. Views my own.
Kieran Didi @DidiKieran
2K Followers 1K Following Research scientist @nvidia and PhD Student in ML at @UniofOxford with @mmbronstein | Learned a lot @Cambridge_CL @emblebi @TBioinf @KnowlesLabCamb
Corey Howe @design_proteins
2K Followers 703 Following Hiring? let’s talk - Building @SeqDesign, Exploring bioengineering and protein design, inspired by evolution and biosolutions
Ariel Amir @Ariel_4321
1K Followers 140 Following Professor of physics, interested in mathematical modeling of living systems and in particular microbial growth
Majdi Hassan @majdi_has
271 Followers 255 Following PhD student @ Mila | ML for chemistry and biophysics
Jorge Bravo Abad @bravo_abad
12K Followers 10K Following Professor @UAM_Madrid Writing on what matters in AI for Science: https://t.co/sNvjOIcqgU "IA para estudiantes de ciencias": https://t.co/Zs5o2gszjj
Simon Olsson @smnlssn
3K Followers 1K Following Associate Professor at @chalmersuniv. @WASP_Research Fellow. ELLIS Member.
Kilian Weinberger @KilianQW
455 Followers 31 Following Professor of Computer Science @ Cornell University Research Scientist at ASAPP working on Machine Learning
Jonas Köhler @jonkhler
2K Followers 551 Following fueled by randomness ml research @cusp_ai, ex-{@MSFTResearch,@GoogleDeepMind,@MPI_IS} born @ 353 ppm, he/him, block toxicityYou might like
