Canvas-to-Image: Compositional Image Generation with Multimodal Controls Paper • 2511.21691 • Published 11 days ago • 32
Agentic Learner with Grow-and-Refine Multimodal Semantic Memory Paper • 2511.21678 • Published 11 days ago • 10
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction Paper • 2511.20937 • Published 11 days ago • 15