Jason Yim

329 posts

Jason Yim banner
Jason Yim

Jason Yim

@json_yim

Past: @Xaira_Thera, @MIT_CSAIL PhD, @GoogleDeepMind. Interests: generative models, LLMs, science.

Cambridge, MA Katılım Eylül 2017
365 Takip Edilen1.8K Takipçiler
Sabitlenmiş Tweet
Jason Yim
Jason Yim@json_yim·
Combining discrete and continuous data is an important capability for generative models. To address this for protein design, we introduce Multiflow, a generative model for structure and sequence generation. Preprint: arxiv.org/abs/2402.04997 Code: github.com/jasonkyuyim/mu… 1/8
GIF
English
2
98
469
74.1K
Jason Yim retweetledi
Peter Holderrieth
Peter Holderrieth@peholderrieth·
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.
Peter Holderrieth@peholderrieth

🚀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: Step-by-step derivations. 📝 Notes: Mathematically self-contained lecture notes 💻 Coding: Hands-on exercises for every component We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models. Everything is available here: diffusion.csail.mit.edu A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints! #MachineLearning #GenerativeAI #MIT #DiffusionModels #AI

English
22
327
3.1K
207.6K
Jason Yim
Jason Yim@json_yim·
@karsten_kreis Congrats! Great to see the progress with codesign and inference time scaling
English
1
0
2
70
Karsten Kreis
Karsten Kreis@karsten_kreis·
📢📢 Proteina-Complexa 📢📢 Atomistic Binder Design with Generative Pretraining and Test-Time Compute + Experimental Validation at Scale ⭐️ Project page (research.nvidia.com/labs/genair/pr…) for: 📜 Method paper (ICLR 2026 Oral) 🧬 Wet lab paper 🛠️ Code & models 📁 Data 🧵 Thread (1/n)
English
3
32
119
11.8K
Jason Yim
Jason Yim@json_yim·
@BoWang87 Congrats Bo and team! It was awesome seeing the progress in real time.
English
0
0
2
87
Jason Yim retweetledi
Bo Wang
Bo Wang@BoWang87·
Today we’re announcing X-Cell — Xaira’s first step toward a virtual cell. 🧬 A foundation model that predicts how gene expression changes under causal perturbations — across cell types, conditions, and even unseen biology. This is not trained on observational atlases. It is trained on interventions. 🧵👇
English
42
146
950
157.4K
Kieran Didi
Kieran Didi@DidiKieran·
📢 We’re launching Proteina-Complexa — and after the Jensen keynote mention, we definitely had to post this thread now ;) Atomistic binder design with generative pretraining + test-time compute, plus large-scale wet-lab validation. Project page: research.nvidia.com/labs/genair/pr… 🧵 1/n
English
13
99
410
45.7K
Amy Lu
Amy Lu@amyxlu·
🫶Sneak peak at our post-AlphaFold3 capabilities. Much, much more cooking in the kitchen 🧑‍🍳👀 Very proud to contribute to this brilliant team. Happy SOTA Tuesday!
Isomorphic Labs@IsomorphicLabs

Today we share a technical report demonstrating how our drug design engine achieves a step-change in accuracy for predicting biomolecular structures, more than doubling the performance of AlphaFold 3 on key benchmarks and unlocking rational drug design even for examples it has never seen before. Head to the comments to read our blog.

English
10
4
189
9.1K
Jason Yim retweetledi
Protenix
Protenix@ai4s_protenix·
🚀 Introducing Protenix-v1, the first open-source model achieving AF3-level performance Highlights: 🔹 Verified inference-time scaling behavior 🔹 RNA MSA & protein template support 🔹 Additional release: Protenix-v1-20250630 trained on a larger dataset 🔹 PXMeter v1.0.0 for transparent evaluation (6k+ complexes, time-split & domain-specific subsets) 🔗 Code: github.com/bytedance/Prot… 🔗 Eval toolkit: github.com/bytedance/PXMe… 🔗 Online server: protenix-server.com
Protenix tweet media
English
12
81
343
49.8K
Jason Yim
Jason Yim@json_yim·
@MartinPacesa The competition should be comparing different filters rather than different generation methods. Generation is a search for binders that pass a filter. It's the filter that's the bottleneck in protein binder design.
English
1
0
8
469
Jason Yim retweetledi
Rohith Krishna
Rohith Krishna@r_krishna3·
Today, we report a method for design of active enzymes, RFdiffusion2, in @naturemethods. For the first time, we are able to design enzymes with native-range catalytic activity. We also are releasing our next frontier model, RFdiffusion3, code 👇
English
7
72
371
47.1K
Jason Yim retweetledi
Cai Zhou @NeurIPS2025
Cai Zhou @NeurIPS2025@zhuci19·
I will be attending NeurIPS @NeurIPSConf in San Diego next week, presenting our new diffusion language model HDLM arxiv.org/abs/2510.08632, and systematic representation guidance for diffusion models REED arxiv.org/abs/2507.08980. I'm also actively looking for research collaborations -- welcome chat if you are interested in discussion ideas or just some casual talks!
English
0
4
43
3K
Jason Yim
Jason Yim@json_yim·
Go work with Michael. He knows the best wines 🍷
Michael Albergo@msalbergo

Also, please share 🤓: I'll be at NeurIPS Dec 4-8. I am hiring PhD students and postdocs this year to start at @Harvard @KempnerInst. We work across problems in ML, applied math, probability, and biology, with the goal of all learning from each other. Find me at @NeurIPSConf, DM me, or shoot me an email! For a flavor of recent topics, see: malbergo.me/papers.html malbergo.me/research-theme…

English
1
1
17
2.8K
Jason Yim retweetledi
Shangyuan Tong
Shangyuan Tong@ShangyuanTong·
Most people assume you need a massive dataset to distill flow models. We challenge that. Is data actually necessary? Or perhaps it is a liability? Introducing FreeFlow: We achieve SOTA (1.49 FID on ImageNet-512) 1-step image generation without a single data sample. 🧵👇[1/n]
Shangyuan Tong tweet media
English
10
76
440
86.3K
Jason Yim retweetledi
Corbin Rosset
Corbin Rosset@corby_rosset·
Microsoft just dropped Fara-7B, its first on device AI Agent that can use your computer just like you would: it clicks, types, fills out forms and completed tasks just by “seeing” the screen. It’s best-in-class in terms of accuracy and cost from yours truly at Microsoft AI Frontiers and you can use it today
Corbin Rosset tweet media
English
21
30
205
106.1K
Jason Yim retweetledi
Jaeyeon (Jay) Kim
Jaeyeon (Jay) Kim@Jaeyeon_Kim_0·
🚨🚨🚨 Now your Masked Diffusion Model can self-correct! We propose PRISM, a plug-and-play approach fine-tuning method that adds self-correction ability to any pretrained MDM! (1/N)
GIF
English
6
49
291
37.5K
Jason Yim retweetledi
Cai Zhou @NeurIPS2025
Cai Zhou @NeurIPS2025@zhuci19·
(1/5) Beyond Next-Token Prediction, introducing Next Semantic Scale Prediction! Our @NeurIPSConf NeurIPS 2025 paper HDLM is out! Check out the new language modeling paradigm: Next Semantic Scale Prediction via Hierarchical Diffusion Language Models. It largely generalizes Masked Diffusion Models (MDM), and provides the progressively denoising capability for each token in the semantic level. Minimal computation overheads, much better results! arxiv: arxiv.org/abs/2510.08632 code: github.com/zhouc20/HDLM
Cai Zhou @NeurIPS2025 tweet media
English
7
55
344
49.9K
Jason Yim retweetledi
Jaeyeon (Jay) Kim
Jaeyeon (Jay) Kim@Jaeyeon_Kim_0·
We introduce a new ''rule'' for understanding diffusion models: Selective Underfitting. It explains: 🚨 How diffusion models generalize beyond training data 🚨 Why popular training recipes (e.g., DiT, REPA) are effective and scale well Co-led with @kiwhansong0! (1/n)
Jaeyeon (Jay) Kim tweet media
English
7
62
420
62.8K
Jason Yim retweetledi
Peter Holderrieth
Peter Holderrieth@peholderrieth·
New work: “GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models”. GLASS generates images by sampling stochastic Markov transitions with ODEs - allowing us to boost text-image alignment for large-scale models at inference time! arxiv.org/pdf/2509.25170 [1/7]
GIF
English
4
62
259
40.9K
Jason Yim retweetledi
Michael Albergo
Michael Albergo@msalbergo·
We've cleaned up the story big time on flow maps. Check out @nmboffi's slick repo implementing all the many ways to go about them, and stay tuned for a bigger release 🤠 arxiv.org/pdf/2505.18825 flow-maps.github.io
Nicholas Boffi@nmboffi

Consistency models, CTMs, shortcut models, align your flow, mean flow... What's the connection, and how should you learn them in practice? We show they're all different sides of the same coin connected by one central object: the flow map. arxiv.org/abs/2505.18825 🧵(1/n)

English
2
22
134
23.1K

Keşfet

@EErives40101 @karsten_kreis @BoWang87 @DidiKieran @amyxlu @MartinPacesa @naturemethods @NeurIPSConf