Aryan Deshwal
@deshwal_aryan
Assistant Professor in Computer Science @UMNews AI to Accelerate Scientific Discovery and Engineering Design
Our recent work on developing a "physics aware" (or convex hull aware) active search method to more efficiently discover stable materials is now published in Materials Horizons! Link to PDF: pubs.rsc.org/en/content/art…
“guidelines for multi-fidelity Bayesian optimization of molecules and materials” check out our News & Views article in Nature Computational Science! was fun to write this summary/news article, with my PhD student Qia, about the fantastic paper of @VictorSabanza, …, @pschwllr,…
Please help with my inventory of RL-trained humanoid whole-body controllers (WBCs) docs.google.com/spreadsheets/d… This will be the raw material for an upcoming blog post that distills the key differences and commonalities.
We are excited about this workshop, please join us if you are interested in AI for science. Please submit an abstract for your work, we have a track for lightning talks for abstracts!
We’re thrilled to announce the workshop “Experimental Design: AI for Science” happening at Stanford University on 3rd and 4th April 2025. The workshop focuses on theory and methodology of AI-based experimental design and its application to science. edai4science.github.io
Excited to share our latest on multimodal AI and agents for drug design and therapeutic reasoning #AAAI2025 @RealAAAI 📅 Monday, 9 AM – AI2ASE: AI to Accelerate Science and Engineering, ai-2-ase.github.io/schedule/ 📅 Tuesday, 10 AM – AI4Research: Knowledge-Grounded Scientific…
The deadline for our AI2ASE workshop is coming up on November 22, 2024 ai-2-ase.github.io/cop/. We invite all submissions at the intersection of AI and science/engineering domains. #AAAI2025
Led by the excellent Yassine Chemingui @Yassine62754892, we will be presenting our paper on "Constraint-Adaptive Policy Switching for Offline Safe RL" at @AAAI conference. Poster Session: Mar 1 (today), 12:30 to 2:30pm Oral Talk Session: Mar 2 (tomorrow), 2 to 3:15pm
Really excited about this new work on Bayesian optimization for antibody design! It works by teaching a generative model how the human immune system evolves antibodies for strong and stable binders.
How do you go from a hit in your antibody screen to a suitable drug? Now introducing CloneBO: we optimize antibodies in the lab by teaching a generative model how we optimize them in our bodies! w/ @gruver_nate @KuangYilun @yucenlily @andrewgwils and the team at @BigHatBio! 1/7
The deadline for our AI2ASE workshop is coming up on November 22, 2024 ai-2-ase.github.io/cop/. We invite all submissions at the intersection of AI and science/engineering domains. #AAAI2025
We are organizing the 4th AAAI @RealAAAI Workshop on AI to Accelerate Science and Engineering. Please consider submitting your work. #AAAI2025
@UMNComputerSci is recruiting tenure-track faculty focusing on "NLP" this year!! Our NLP presence is yet small, but plans to expand! If you have strong students in your lab, please encourage them to apply or contact me. Please come work with us. Retweets are appreciated. #NLProc
We're hiring computer science faculty! We're looking for outstanding candidates with research & teaching interests in multiple areas, like natural language processing and theoretical foundations of computer science! Learn more and apply here: z.umn.edu/facultyrecruit…
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines ift.tt/PgEMZzX
I've found measure theory particularly helpful as a framework for thinking about sums of discrete + continuous probability distributions. Both of my source separation papers are grounded in intuitions from measure theory: arxiv.org/abs/2002.07942 arxiv.org/abs/2105.08164
We're hiring computer science faculty! We're looking for outstanding candidates with research & teaching interests in multiple areas, like natural language processing and theoretical foundations of computer science! Learn more and apply here: z.umn.edu/facultyrecruit…
📜 two very interesting, fundamental papers that shed light on when multi-fidelity (MF) Bayesian optimization (BayesOpt) is fruitful, compared to single-fidelity (SF) BayesOpt. arxiv.org/pdf/2410.00544 (led by @loic_roch, @pschwllr) arxiv.org/abs/2409.07190 (led by @JelfsChem)…
in our paper in Digital Discovery, we [within a computer simulation] demonstrate multi-fidelity Bayesian optimization (MFBO) for reducing the cost of materials discovery and orchestrating "self-driving" labs. pubs.rsc.org/en/content/art… 🧪 problem setup we (1) wish to search a…