| title | V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning |
|---|---|
| authors | Haoxiang Sun, Zhihang Yi, Langxuan Deng, Yuhao Zhou, Peiqi Jia, Jian Zhao, Li Yuan, Jiancheng Lv, Tao Wang |
| date | 2026-06-24 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.25319 |
| affiliation | Sichuan University |
| upvotes | 25 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions. Existing agentic methods typically rely on reinforcement learning with verifiable rewards or supervised fine-tuning on large-scale annotated reasoning traces, leading to costly exploration, hand-designed verification rules, or heavy dependence on textual supervision. A natural way to avoid such external answer labels is to learn from trajectories sampled by the student itself, which points to On-Policy Distillation (OPD). To understand what OPD can and cannot provide for visual reasoning, we revisit it as negative-free stop-gradient alignment. This perspective shows that, although OPD provides effective token-level correction, its ceiling is constrained by the absence of trajectory-level discrimination. Motivated by these observations, we propose V-Zero, an answer-label-free framework for visual reasoning with contrastive evidence gating. V-Zero uses no annotated textual answer labels; instead, during training it pairs a question-relevant regional crop with a negative visual view to evaluate student-sampled trajectories and gate dense token-level distillation. Experiments on multiple visual reasoning benchmarks show that V-Zero consistently improves fine-grained visual reasoning while preserving strong generalization. Notably, V-Zero is more than 5times faster than previous supervised fine-tuning methods and more than 10times faster than reinforcement learning baselines. Code and dataset will be released at https://github.com/eVI-group-SCU/V-Zero |
cite
@misc{sun2026v,
title={V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning},
author={Haoxiang Sun and Zhihang Yi and Langxuan Deng and Yuhao Zhou and Peiqi Jia and Jian Zhao and Li Yuan and Jiancheng Lv and Tao Wang},
year={2026},
eprint={2606.25319},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.25319}
}