Author

Tian-Le Zheng

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

VDiff-Bench provides a targeted diagnostic for evaluating comparative visual understanding in MLLMs, exposing failures that are not captured by standard single-image vision-language tasks.

Yixin Wan, Tian-Le Zheng, Kai-Wei Chang · 0 citations