Alibaba / Qwen Team

“Qwen3-VL-4B (Bai et al. 2025) introduced the concept of treating bounding box coordinates as tokens, allowing for explicit grounding”

“CSD provides explicit task-conditioned spatial supervision before action learning... The teacher is used exclusively to estimate the target-object center from the original RGB observation and task instruction... Qwen3-VL-4B and explicit coarse spatial labels are not used during downstream policy training or deployment”