Zeliang Zhang

8

Papers

51

Total Citations

Papers (8)

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

One Forward is Enough for Neural Network Training via Likelihood Ratio Method

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

Understanding Model Ensemble in Transferable Adversarial Attack

Targeted Forgetting of Image Subgroups in CLIP Models

π-AVAS: Can Physics-Integrated Audio-Visual Modeling Boost Neural Acoustic Synthesis?

Learning to Transform Dynamically for Better Adversarial Transferability