3 papers
cs.CV2025
Discovering Influential Neuron Path in Vision Transformers
Yifan Wang, Yifei Liu, Yingdong Shi +5
Vision Transformer models exhibit immense power yet remain opaque to human understanding, posing challenges and risks for practical applications. While prior research has attempted…
cs.CV2025
Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
Yingdong Shi, Changming Li, Yifan Wang +5
Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases…
cs.CV2024
SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
Chunlin Yu, Hanqing Wang, Ye Shi +4
3D affordance segmentation aims to link human instructions to touchable regions of 3D objects for embodied manipulations. Existing efforts typically adhere to single-object, single…