Xiaomi-Lens-0 adds mask prediction to a 4B Qwen3.5 model
A lightweight decoder turns the model's own visual latents into masks, lifting referring comprehension 5.6 points over Qwen3.5.
1 stories, newest first · one card per story
A lightweight decoder turns the model's own visual latents into masks, lifting referring comprehension 5.6 points over Qwen3.5.
Today 1K readers · 1.5K views · 1.1K reads · all time 159K views