- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Noisy Student On-Policy Self-Distillation (NOPD) for post-training vision-language models without ground-truth answers or an external teacher. The student generates on-policy responses from corrupted images, while the same model, conditioned on the corresponding clean images and student-generated prefixes, provides token-level supervision. Experiments report improvements over base models across various benchmarks, with performance comparable to or better than RLVR and external-teacher on-policy distillation on several reasoning benchmarks.
Critical strengths
- The paper presents a simple approach to VLM self-improvement without ground-truth answers or an external teacher, which is a relevant research topic on post-training of VLM.
- The ablations support key design choices, and the experiments cover both reasoning and broader VLM benchmarks.
- The paper is generally well-written and easy to follow.
Critical weaknesses
- Comparisons with SSL4RL [1] and Visual Jigsaw [2] are missing, as both enable post-training without human-provided answers or external teachers. Image Jigsaw reports 84.45 on MMBench-EN, versus NOPD's 83.6 on MMBench-EN, which raise a doubt on the effectiveness of NOPD.
- Some formatting issues, the margin between Sec.5 and Sec.6 are quite small which could be adjusted for readability.
[1] Guo et al. SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning. ICML 2026.
[2] Wu et al. Visual Jigsaw Post-Training Improves MLLMs. ICLR 2026.
Questions for authors
- Can the authors compare the performance NOPD with SSL4RL and Visual Jigsaw under matched backbones, data?
- Will the authors release the training and evaluation code in the revised version of this paper?
I would consider raising my score if the questions are addressed.