arXiv Machine Learning August 4, 2026 By Leyan Xue, Feng Xiong, Mingjun Ma, Changqing Zhang

Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models

Read the original on arXiv Machine Learning →

arXiv:2608. 01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-token distributions at prefixes along those trajectories.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computer Vision

Sep 3

CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction

CA-OPD is a confidence‑aware on‑policy distillation framework that improves structured visual prediction by using teacher confidence to selectively correct unreliable student transitions and gradually transfer rollout control to the student. The method aligns supervision with intervention decisions, providing direct cross‑entropy loss for corrected tokens and full predictive distribution for retained tokens. In a multi‑teacher setting for GUI grounding and OCR, CA‑OPD significantly outperforms the Qwen3.5‑0.8B baseline, achieving large gains on benchmarks such as ScreenSpot‑Pro and OCRBench‑v2 English.

By Menghao Li, Linjie Mu, Yin Wang, Haotian Hu, Yannian Gu, Lujiayi Xue, Fanyi Wang

llms efficiency benchmarks

arXiv Computer Vision

3d ago

Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation

arXiv:2609.39120v1 Announce Type: new Abstract: On-policy distillation (OPD) improves reasoning by providing token-level supervision from a teacher on a student's own trajectories. Existing methods p...

By Siyuan Liu, Kanghui Tian, Yue Duan, Yutao He, Shangdong Yang, Jian Zhang, Yinghuan Shi

efficiency multimodal benchmarks

arXiv Computer Vision

Aug 26

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

arXiv:2606.18974v3 Announce Type: replace Abstract: Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly a...

By Pengyu Li, Zhitao Gao, Lingling Zhang, Muye Huang, Yuanming Li, Fangzhi Xu, Jun Liu

diffusion efficiency multimodal benchmarks

Hugging Face Trending Papers

Jun 17

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference cost from multi-step diffusion.

diffusion efficiency multimodal benchmarks

arXiv AI

Jun 3

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

arXiv:2605. 18740v4 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image.

By Qianhao Yuan, Jie Lou, Xing Yu, Hongyu Lin, Le Sun, Xianpei Han, Yaojie Lu

llms agents efficiency multimodal benchmarks

arXiv Computation and Language

Sep 10

On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data

arXiv:2609.10321v1 Announce Type: new Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...

By Hongyuan Zhang, Xianda Guo, Yanlun Peng, Qianlong Yang, Yubin Guo, Pinhan Fu, Mulin Chen, Xiaozhen Qiao, Ping Luo

llms efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction

Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation

On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data