Chenru Duan

New paper alert: React-OT: Optimal Transport for Generating Transition State in Chemical Reactions (arxiv.org/abs/2404.13430). React-OT formulates TS search as a transport problem, approaching chemical accuracy while taking only 0.5 seconds in inference on a single GPU. #compchem

Bye Qwen3-235B-A22B, hello Qwen3-235B-A22B-2507! After talking with the community and thinking it through, we decided to stop using hybrid thinking mode. Instead, we’ll train Instruct and Thinking models separately so we can get the best quality possible. Today, we’re releasing…

Thrilled to be awarded the 2024 @ChenInstitute and @ScienceMagazine Prize for AI Accelerated Research! This is a huge recognition for our past work on structure prediction foundation models, and the path ahead to pursue further. Looking forward to presenting more this October!

🔥 Hot off the press in Advanced Science! We pit 7 ML interatomic potentials against React-OT, a diffusion model, and show generative AI makes TS search faster, cheaper, smarter. 🚀 Why it matters👇 • Again, a low MAE on energy and force is not all we need for locating…

🚨 Postdoc Hiring: I am looking for a postdoc to work on rigorously evaluating and advancing the capabilities and safety of computer-use agents (CUAs), co-advised with @ysu_nlp @osunlp. We welcome strong applicants with experience in CUAs, long-horizon reasoning/planning,…

AI for Science will be returning to @NeurIPSConf 2025! We aim to bring together scientists and AI researchers to discuss the reach and limits of AI for Scientific Discovery 🚀 📖 Workshop submission deadline: Aug 22 💡 Dataset proposal competition: more details coming soon

If you have ideas fallen under the scope of iterative scienitific discovery, let me know!

🆕 LLM-EO @DeepPrinciple now hot off the press in @J_A_C_S! We marry Large Language Models with evolutionary optimization, LLM-EO, for hands-free design of transition-metal complexes. Why it matters • Sample-efficient: just 200 evaluations net 8 / 20 global top-scoring Pd(II)…

🎉 We’re thrilled to announce that Deep Principle has been selected as a 2025 World Economic Forum Technology Pioneer! 🌍 Each year, the WEF recognizes early-stage companies poised to make a significant impact on business and society. We’re proud to be recognized alongside…

Who said #chemistry has revealed all its secrets? Just when we thought we knew everything about good old nitrogen, scientists report a new and fascinating allotrope in @Nature. nature.com/articles/s4158…

[1/9]🚀Excited to share our new work, RNE! A plug-and-play framework for everything about diffusion model density and control: density estimation, inference-time control & scaling, energy regularisation. More details👇 Joint work with @jmhernandez233 @YuanqiD, Francisco Vargas

Thanks Victoria for featuring our React-OT work in Chemistry World, "AI predicts transition states with exceptional precision"(chemistryworld.com/news/ai-predic…)

Scientific Knowledge Emerges in LLMs and YOU CAN Access It (via sampling)! 🔥🔥🔥New blog to summarize what we have learned from evaluating LLMs for several optimization, decision-making, and planning problems in science with truly impressive performances!

Join us at the #ACSSpring2025 symposium with @WenhaoGao1 , @chenru_duan , @zhongpc and @cwcoley and great speakers exploring generative modeling for molecular science! ⏰ March 26-27, 2025 📍 Ballroom 6C (San Diego Convention Center) Agenda 👉 acs.digitellinc.com/live/34/sessio…

Saw the #o1pro api pricing - shocked. It is Hermes in LLM. We are planning a large-scale multi institution benchmark on llm for scientific discovery. @OpenAI is your strategy to make it expensive enough so that no one can afford benchmarking it?