2 papers
cs.AI2026
Diffusion-CAM: Faithful Visual Explanations for dMLLMs
Haomin Zuo, Yidi Li, Luoxiao Yang +1
While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lag…
stat.ML2025
On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration
Yirui Zhou, Yunfei Jin, Xiaowei Liu +2
Learning from observations (LfO) replicates expert behavior without needing access to the expert's actions, making it more practical than learning from demonstrations (LfD) in many…