Intern@google .PhD student @ucsd_cse. Into AI for Science, especially climate&weather.
San Diego
Joined May 2021
- Tweets131
- Following833
- Followers539
- Likes1.6K
Pinned Tweet
Sharing a blog post about our #Neurips2023 paper "DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting"
salvarc.github.io/blog/2023/…
It's faster than standard diffusion models, has low memory needs, and generates stable & probabilistic rollout forecasts. 1/7
Salva Rühling Cachay retweeted
Hello everyone! I'm organizing a short but intensive 1 month virtual seminar in October targeted to LatinAmerica undergraduates to help them prepare for their PhD/Masters applications in STEM fields (limited availability)! Please feel free to share🫡 luma.com/bqdqfpoh
Salva Rühling Cachay retweeted
Excited to share WeatherNext 3 from @GoogleDeepMind and @GoogleResearch!
High-res temperature and precipitation forecasting using the latest satellite observations 🛰️
It's also the best global weather model according to Brightband's live leaderboard!
owb.brightband.com/
Salva Rühling Cachay retweeted
I am excited to finish postdoc @yuqirose's lab and start as an assistant professor of computer science at UCF;
I'm hiring fully funded PhD students and postdocs.
Join me if you want to push the frontier of ML for science and engineering.
eydcao.github.io/#joining
ALT Our lab features applications including physics based simulators, and more, to be learned by ML or operated by AI agents. Fig from SimuCost Benchmark.
Salva Rühling Cachay retweeted
🌎⚡ A frontier (1.5°, 15-day) ensemble weather forecast in ~3 seconds, from a probabilistic model you can train in ~1 day on a single H200 GPU?*
Meet U-Cast, our new #ICML2026 paper. 🧵
Salva Rühling Cachay retweeted
[🚨ICML 2026 Paper Alert] Excited to introduce SimulCost! 🚀 The first cost-aware benchmark and toolkit for evaluating LLM agents on complex physics simulations.
Can LLMs efficiently tune complex physics simulators under realistic computational budgets? Spoiler: They struggle! 📉
🔗 Project: sichenglai.com/SimulCost-Web…
📄 Paper: arxiv.org/abs/2603.20253
💻 Code: github.com/Rose-STL-Lab/Simu…
🤗 Models: huggingface.co/datasets/Rose…
Huge thanks to the amazing team: @YadiCao, Sicheng Lai, Yang Zhang, Zach Lawrence, Rohan Bhakta, Izzy F. Thomas, Mingyun Cao, Chung-Hao Tsai, Zihao Zhou, Yidong Zhao, Hao Liu, Alessandro Marinoni, Alexey Arefiev, @yuqirose
A quick thread 🧵👇
🌎⚡ A frontier (1.5°, 15-day) ensemble weather forecast in ~3 seconds, from a probabilistic model you can train in ~1 day on a single H200 GPU?*
Meet U-Cast, our new #ICML2026 paper. 🧵
*Fine-tuning takes ~1 day (1.2 H200-GPU-days) on a pre-trained deterministic backbone; add ~7 H200-days to train that backbone from scratch (~8 total).
📄 arxiv.org/abs/2604.09041
💻 github.com/Rose-STL-Lab/u-ca…
Really appreciate the computational support from @modal !!
some people use @modal to predict the next token, others to predict the next rainstorm
arxiv.org/abs/2604.09041
Salva Rühling Cachay retweeted
some people use @modal to predict the next token, others to predict the next rainstorm
arxiv.org/abs/2604.09041
NeurIPS poster session tomorrow morning!⚡️
Come say hi if you are interested in diffusion/AI4Science/PDEs/weather/etc.
⏰ Friday, 11am-2pm PST at Poster #3614
Happy to chat outside these hours as well—I'm here for the full week (and the next ;)
🌍 Modeling chaos isn't just about predicting the next step—it's about modeling how uncertainty grows over time.🌪️
I’m thrilled to share Elucidated Rolling Diffusion Models (ERDM), accepted to #NeurIPS2025!
We unify rolling diffusion with EDM for forecasting complex systems🧵👇
𝗧𝗵𝗲 𝗥𝗲𝘀𝘂𝗹𝘁𝘀: 3) 𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗥𝗲𝗮𝗹𝗶𝘀𝗺: ERDM matches the power spectra of operational physics-based models (IFS ENS), solving the "blurriness" problem common in AI weather models.
A huge thank you to my brilliant collaborators @NVIDIAAI -Miika Aittala, @karsten_kreis, Noah Brenowitz, @ArashVahdat & @MardaniMorteza-and @yuqirose @ucsd_cse
👇 See you next week in San Diego! Paper: arxiv.org/abs/2506.20024
