OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
Researchers introduce OmniVChat, a native audio-visual dialogue task with a synthesis studio, benchmark, and RL reward design that improves Qwen3-Omni-Instruct.
1 stories, newest first · one card per story
Researchers introduce OmniVChat, a native audio-visual dialogue task with a synthesis studio, benchmark, and RL reward design that improves Qwen3-Omni-Instruct.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views