arXiv:2607. 04112v1 Announce Type: cross Abstract: Multimodal LLMs struggle to systematically model the temporal evolution of visual scenes in videos or multi-image sequences.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood.
arXiv:2607. 14187v1 Announce Type: new Abstract: Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved.
Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We introduce Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination.
arXiv:2607. 26452v1 Announce Type: new Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually capture only part of this structure.
WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction.
arXiv:2606. 26217v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs), including recent LeWorldModel (LeWM), have become a promising foundation for reconstruction-free visual world models.