Shuangqi Li

2 accepted papers

2026

Learning to Weight Parameters for Training Data Attribution

Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann

ICLR 2026poster

We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian approximations, which do not fully model functional heteroge…

Cited by 0 Source ↗Scholar ↗

2025

Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds

Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann

ICLR 2025spotlight

Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin on the right of a bowl". Understanding these inconsistencies…

Cited by 1 Source ↗PDF ↗Scholar ↗