A position paper outlining five layers of functional unification for multimodal understanding and generation: inputs, representations, reasoning, optimization, and evaluation.
Sep 30, 2026

A position paper on consistency across multimodal grounding, representations, reasoning, post-training, and evaluation.
Feb 3, 2026
A survey of multimodal foundation model evaluation from a hierarchical perspective, covering a broad range of applications.
May 1, 2025