这篇论文提出了VCSD，不需要外部老师就能让多模态模型自己教自己，在Qwen3-VL上几个规模都涨了4-5个点，而且不增加推理成本。
VCSD提出一种新的自蒸馏方法，通过对比原始图像和内容擦除控制的token级log概率差异来生成蒸馏信号。在ViRL39K数据集上，基于Qwen3-VL的实验显示，2B模型七基准聚合从62.27%提升至67.04%，4B从71.30%提升至73.16%，8B从72.51%提升至76.26%。VCSD无需外部教师、特权答案或视觉证据信号，且不增加推理开销。
Visual Contrastive Self-Distillation
On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student. Existing methods create this asymmetry either through privileged answers or visual evidence. We ask whether both can be removed, yielding a simpler form of OPSD driven purely by input conditioning. For this purpose, we propose Visual Contrastive Self-Distillation, namely VCSD, which converts image-content removal into an on-policy self-distillation signal. At each student-generated response prefix, the EMA teacher produces two next-token distributions under the same prompt and prefix -- one conditioned on the original image and the other on a content-erased control. Their token-wise log-probability difference highlights candidates whose likelihood is specifically increased by the instance-level visual content. We use this contrast to sharpen the teacher's original-image distribution within its plausible support, and distill the resulting full-distribution target into the student. Using ViRL39K dataset, VCSD consistently outperforms matched OPSD across Qwen3-VL and Qwen3.5 models. For example, on Qwen3-VL, it improves the seven-benchmark aggregate from $62.27\% \rightarrow 67.04\%$ at 2B, $71.30\% \rightarrow 73.16\%$ at 4B, and $72.51\% \rightarrow 76.26\%$ at 8B. Furthermore, VCSD requires no external teacher, privileged answers, visual evidence signals, reasoning traces, or additional inference-time cost.