Tim Z. Xiao

PhD student, Max Planck Institute for Intelligent Systems, Max-Planck Institute

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Reparameterized LLM Training via Orthogonal Equivalence Transformation

#909 · Zeju Qiu, Simon Buchholz, Tim Z. Xiao, Maximilian Dax, Bernhard Schölkopf, Weiyang Liu

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Value Gradient Guidance for Flow Matching Alignment

#4906 · Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich, Weiyang Liu, Dinghuai Zhang

We propose a value gradient matching formulation for reward finetuning/alignment for flow matching models with the theory of optimal control, and empirically verify our method on the popular text-to-image flow matching model StableDiffusion3