Jianke Yang

[Jung Yeon Park @park_jungy]

(1/8) Happy to share that our paper LieFlow has been accepted to #ICML2026.

Symmetry is a strong inductive bias in ML, but you have to know the symmetry in advance. Can a model discover it directly from data, for both discrete and continuous groups? 🧵

[Tycho van der Ouderaa @tychovdo]

🌟New work: Noether's razor⭐️ Our NeurIPS 2024 paper connects ML symmetries to conserved quantities through a seminal result in mathematical physics: Noether's theorem. We can learn neural network symmetries from data by learning associated conservation laws. Learn more👇. 1/16🧵

[Jianke Yang @jiankeyang]

@yuqirose Join us in our poster representation today 1:30-3:00pm at Hall C 4-9 #310!

[Yichi Zhang @yichizhang_19]

Introducing MultiTrust by Tsinghua ! 🚀

Benchmarking over 20 MLLMs on multi-aspects of trustworthiness,from multi-perspectives in their multimodal risks and cross-modal impacts.

👉 Explore more at https://t.co/L34u89I5Gu

#TrustworthyAI #SafeAI #MLLM #GPT4V #MultiTrust

[Rose Yu @yuqirose]

How to discover complex #symmetry from high-dimensional dynamical systems? Check out our #ICML2024 paper on ``Latent Space Symmetry Discovery''!

Paper: https://t.co/XXTXDNosno
Code: https://t.co/Ozhq7x6HFz
(1/3)

[Honglu Zhou @zhou_honglu]

📢 Our #SMART101 challenge is now open! 🎉 Join the brightest minds in multimodal reasoning and cognitive models of intelligence to drive AI progress. 🚀 Don't miss out! Challenge closes on Sept. 1. Winning teams will receive prizes! 🏆 https://t.co/asTC5oscJh
#VLAR #ICCV2023 #AI