exploring vision language agents as text-to-scene generators
towards human-level interpretable visual physical reasoning and physical concept learning abilities on softbody and fluid
a device to discern the correlation between visual stimuli and cortex neuron activities
photorealistic audio-driven hand gesture generation solution with personalized registration
a cool solution of matching Taobao cloth color descriptions with its showcase images
a robot serving user on desktop with multiple functions and control methods for both work and fun