2 citations · 3 across the 12 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
EAR: Erasing Concepts from Unified Autoregressive Models
Haipeng Fan, Shiyuan Zhang, Baohunesitu +2
Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR mo…
cs.CV2025
TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models
Zeqing Wang, Shiyuan Zhang, Chengpei Tang +1
Reasoning about temporal causality, particularly irreversible transformations of objects governed by real-world knowledge (e.g., fruit decay and human aging), is a fundamental aspe…