🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

“Molecule generation with fragment retrieval augmentation” Cool work building on top of the SAFE and SAFE-GPT work that we presented last NeurIPS. We’ll be presenting “SAFE setup for molecular design” at the AI4Mat workshop. Emmanuel Noutahi Lu Zhu arxiv.org/abs/2410.20232

Interesting... ByteDance (tiktok) taking on AlphaFold 3 github.com/bytedance/Prot… 🧬🖥️🧪

Using mechanistic #interpretability 💻 to advance scientific #discovery 🧪 & capture striking biology? 🧬 Come see Jason Hartford's oral presentation 👨‍🏫 @ #NeurIPS2024 Interpretable AI workshop 🦾 to learn about extracting features from large 🔬 MAEs! 📄: openreview.net/forum?id=jYl7k…

Congratulations to Seul Lee Seul Lee for receiving the 2025-2026 NVIDIA PhD fellowship. blogs.nvidia.com/blog/graduate-…

GenMol: A Drug Discovery Generalist with Discrete Diffusion (by NVIDIA) Very simple categorical diffusion model used to generate molecules. No comparisons against standard models (e.g. SMILES-based LSTM); No FCD; but seems to work. arxiv.org/abs/2501.06158

GenMol: A Drug Discovery Generalist with Discrete Diffusion 1. GenMol introduces a versatile framework for drug discovery by leveraging discrete diffusion and the SAFE molecular representation. This allows for efficient and effective handling of various tasks in the drug

A true generalist model for small molecule generation is here! Read more about #GenMol: developer.nvidia.com/blog/evaluatin…

The NVIDIA GenMol NIM redefines versatility in molecular design, with 35% faster sampling than SAFE-GPT. It's shown high benchmarking performance for: - Lead optimization - De novo generation - Linker design - Motif extension - Superstructure generation - Scaffold decoration

Can discrete diffusion-based generative models outperform GPT-based next-token predictive models in molecular tasks? Learn about GenMol, NVIDIA’s new #DrugDiscovery Swiss Army Knife! paper: arxiv.org/abs/2501.06158 blog: developer.nvidia.com/blog/evaluatin… demo: build.nvidia.com/nvidia/genmol-…

📣 GenMol has arrived. Learn how GenMol speeds up large-scale #drugdiscovery, thanks to its parallel decoding and fragment remasking strategy. Compare it side-by-side with SAFE-GPT in our blog. #NVIDIANIM #NVIDIAhealthcare Deep dive in our blog ➡️ nvda.ws/4hgTrnX

🔥 GenMol: Travel through chemical space with an efficient fragment-based representation, modern discrete diffusion, and enhanced exploration via fragment re-masking and re-generation! 🔥 paper: arxiv.org/abs/2501.06158 blog: developer.nvidia.com/blog/evaluatin… demo: build.nvidia.com/nvidia/genmol-…

Can a single AI model effectively handle multiple drug discovery tasks while outperforming specialized models in each area?arXiv.org NVIDIA "GenMol: A Drug Discovery Generalist with Discrete Diffusion" • SAFE-GPT, the existing state-of-the-art model, is limited by its

🚨Announcing our #ICLR2025 Oral! 🔥Diffusion LMs are on the rise for parallel text generation! But unlike autoregressive LMs, they struggle with quality, fixed-length constraints & lack of KV caching. 🚀Introducing Block Diffusion—combining autoregressive and diffusion models

Hi everyone, we are so back! Delighted to announce the 2nd Generative AI and Biology (GenBio) Workshop ICML Conference #icml2025! Join us in this exciting discourse on all aspects of the future of #GenerativeAI and Biology!! 🧬🚀 Website: genbio-workshop.github.io/2025/ 1/n

We invite submissions including, but not limited to: biomolecules and biosystems design, algorithm innovations for biological data, large-scale foundation models, and more! For more details, please check our call for paper: genbio-workshop.github.io/2025/index.htm… Deadline: May 20th 2/n

Thrilled to share our amazing speakers! Institute for Protein Design, Jennifer Listgarten, James Collins, Mengdi Wang, Marinka Zitnik, Eric Xing. More to be announced! 3/n

Finally, our amazing organizers: Minkai Xu Zhenqiao Song, Yist YU, Wenxian Shi, Seul Lee, Maria Brbic, Aditi Krishnapriyan, Regina Barzilay, Stefano Ermon, Lei Li! Stanford AI Lab Language Technologies Institute | @CarnegieMellon MIT Jameel Clinic for AI & Health Berkeley AI Research 4/n, n=4