每天自动聚合 AI 领域最新动态
Physical reasoning underpins how embodied systems understand and act in the physical world, yet vision-language model...
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. How...
Safe household navigation requires robots to regulate clearance and speed according to what an obstacle is and how cl...
Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that pre...
Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but ...
Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments u...
Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a r...
When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory k...
Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of t...
Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for mul...
Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimod...
How much of zero-shot benchmark accuracy is captured by word-level alignment between a pre-training corpus and the be...