Ruichen Xu

News

• [2026.01] 🎉 Our paper IAGA: Identity-Aware Gaussian Approximation for Efficient 3D Molecular Generation was accepted to ICLR 2026. Big thanks to my friend Jingxiang (JingXiang) Qu!
• [2026.01] I will teach AMS 361 in Winter 2026. The syllabus is available here.
• [2025.09] Chloe Cho’s paper on HNN denoising via Fourier filter was accepted to IEEE URTC.
• [2025.09] Our workshop paper IAGA: Identity-Aware Gaussian Approximation for Efficient 3D Molecular Generation was accepted to SPIGM @ NeurIPS 2025. Congrats to my friend Jingxiang!
• [2025.08] Three papers accepted to NYSDS 2025 — 1 oral + 2 posters. I am the co-corresponding author on all three papers, working with Max Cederholm, Claire Yu, and Albert Ding:
  • Boundary-Informed Method of Lines for Physics-Informed Neural Networks — Oral presentation.
  • Velocity-Inferred Hamiltonian Networks: Symplectic Dynamics from Position-Only Observations — Poster.
  • Physics-Informed Active Learning via Functional Simulated Annealing for Neural Operator — Poster.
• [2025.08] Submitted two papers to MIT URTC 2025 with Aiden Kwon and Chloe Cho (Garcie Scholar program). Congrats to the students!
• [2025.08] Submitted three papers to NYSDS 2025 with Albert Ding (Simons Scholars), Max Cederholm, and Claire Yu (Garcie Scholar program). Very good summer work with high school students!
• [2025.07] RL-QESA: Reinforcement-Learning Quasi-Equilibrium Simulated Annealing — AI4Math @ ICML 2025 (Poster). Very happy to share this was presented.
• [2025.06] APOD: Adaptive PDE-Observation Diffusion for Physics-Constrained Sampling — ICML 2025 — Assessing World Models Workshop. Excited this was accepted and presented.
• [2025.06] SP: Learning Physics from Sparse Observations — Three Pitfalls of PDE-Constrained Diffusion Models — ICML 2025 — Assessing World Models Workshop. Pleased to share acceptance.
• [2025.06] Dynamic Schwartz-Fourier Neural Operator for Enhanced Expressive Power — Transactions on Machine Learning Research (TMLR). Happy to see this accepted.
• [2025.06] An Iterative Framework for Generative Backmapping of Coarse-Grained Proteins — GenBio 2025 (Poster). Delighted this work is out.
• [2025.05] Kolmogorov–Arnold Representation for Symplectic Learning: Advancing Hamiltonian Neural Networks — IJCNN 2025 (Accepted, co-first author). IEEE Xplore link pending — will update once live. (arXiv)
• [2025.01] Discretization-invariance? On the Discretization Mismatch Errors in Neural Operators — ICLR 2025 (Poster). Thrilled to have this at ICLR.
• [2024.10] Coordinate Transform Fourier Neural Operators for Symmetries in Physical Modelings (CT-FNO) — Transactions on Machine Learning Research (TMLR). Glad to have this one in TMLR.

Tip: Keep items short and timestamped (e.g., [YYYY.MM]). Move older items to an archive if the list grows long.