I guess it also depends on the domain and action space. E.g. even in AV I'd expect Gaussians on yaw/vel to be enough, but for juke/jerk we probably want multimodal distributions.
03.01.2025 13:52 — 👍 0 🔁 0 💬 0 📌 0
In my (very limited) experience: i) You can get multi-modality on trajectory level even with unimodal Gaussians, so actions being MM isn't as important. ii) When I was using a GMM, nearly all modes collapsed and it was basically a Gaussian + slightly more robust to outliers.
03.01.2025 07:26 — 👍 1 🔁 0 💬 2 📌 0
Foundation Models for Generalizable Autonomy.
Assistant Professor in AI Robotics, Georgia Tech
prev Berkeley, Stanford, Toronto, Nvidia
ML for Science, Interpretability & GNNs. Jun.-Prof. @ KIT. ML-Group @ Heidelberg Institute for Theoretical Studies. Previously Samsung AI, Microsoft Research, MIT-CSAIL, TUM & Caltech. Opinions and typos are my own.
Physics + Machine Learning
Scientist at SLAC National Laboratory at Stanford
Bioinformatics Scientist / Next Generation Sequencing, Single Cell and Spatial Biology, Next Generation Proteomics, Liquid Biopsy, SynBio, Compute Acceleration in biotech // http://albertvilella.substack.com
MIT CSAIL | Co-created AIs: CICERO, Diplodocus | Ex: Google, FAIR, MSR
AI for Science, deep generative models, inverse problems. Professor of AI and deep learning @universitedeliege.bsky.social. Previously @CERN, @nyuniversity. https://glouppe.github.io
Research Scientist at Niantic
Interests: CV, ML, DL, 3D reconstruction, image matching, Gaussian splatting, rendering
ericzzj1989.github.io
PhD from CUHK. 3D vision, SLAM, SfM, Image Matching (https://github.com/ericzzj1989/Awesome-Image-Matching).
Parent, spouse, Australian, Professor of Machine Learning in Oxford. Long Covid, trans rights, music, reggae on Fridays, AI must be good for humans, https://www.robots.ox.ac.uk/~mosb
RS DeepMind. Works on Unsupervised Environment Design, Problem Specification, Game/Decision Theory, RL, AIS. prev CHAI_Berkeley
RL researcher at DeepMind
https://schaul.site44.com/ 🇱🇺
Professor of Computer Science at Oxford. Senior Staff Research Scientist at Waymo.
#RobotLearning Professor (#MachineLearning #Robotics) at @ias-tudarmstadt.bsky.social of
@tuda.bsky.social @dfki.bsky.social @hessianai.bsky.social
Blog: https://sander.ai/
🐦: https://x.com/sedielem
Research Scientist at Google DeepMind (WaveNet, Imagen 3, Veo, ...). I tweet about deep learning (research + software), music, generative models (personal account).
Research in AI/ML at Google DeepMind. Touche-à-tout.
FR/US/GB AI/ML Person, Director of Research at Google DeepMind, Honorary Professor at UCL DARK, ELLIS Fellow. Ex Oxford CS, Meta AI, Cohere.
AI @ OpenAI, Tesla, Stanford
AI @ Pacific Fusion. Climate change monomaniac.
PhD @ Oxford. Prev: Carbon Re, DeepMind, FAIR, MSR, […]
🌍 / 🇪🇺 / 🇮🇹 / he / him.
Website: arbitrarygravitas.com
