Wenyuan Zhang

Higher resolution in real-time audio-visual interactions can be achieved without sacrificing latency, enabling clearer agent representation in conversations.

Sub-second duplex audio-visual communication is now achievable with a single, unified model that eliminates the latency of traditional cascaded systems.

SuperFashion achieves up to 9.35% improvement in fashion image retrieval by leveraging superpixel tokens for enhanced attribute localization.