Fei Su

Uruqi: Learning Spatial Cognition from Visual Experience

Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own motion to interpret changes across observations and update object locations and spatial relations accordingly. Despite spatial post-training having substantially broadened...

From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning

This work presents a new perspective that views primitive variations as the context-driven activation of concrete visual cues rather than independent entities rather than independent entities, and proposes CLEAR, a CLoze-style rEAsoning-based Re-ranking framework inspired by human perceptual processes.

SAG: Spatial-Attention-Guided Motion Customization for text-to-video Diffusion Models