arXiv AI

On-Policy Visual Evidence Distillation

arXiv AI
Sep 16

OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation

OPD‑Aha is a privileged on‑policy distillation method that improves multimodal reasoning by reconstructing the distillation target from the teacher’s isolated visual preference instead of relying on fragile teacher‑student discrepancies. It suppresses continuations that contradict the image, encouraging students to interrupt flawed reasoning with reflection tokens such as "wait" and "actually." This approach leads to consistent improvements across fine‑grained perception and complex multimodal reasoning benchmarks.

By Chenhao Qiu, Dawei Li, Yechao Zhang, Lei Gong, Zhen Tan
Hugging Face Trending Papers
Aug 9

OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories

Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision.

arXiv Machine Learning
Oct 12

CV-OPD: Contrastive Vision On-policy Distillation

The paper introduces Contrastive Vision On‑policy Distillation (CV‑OPD), a method that enhances on‑policy distillation for vision‑language models by adding a contrastive divergence loss and a discrepancy‑aware gating mechanism. CV‑OPD contrasts teacher distributions from positive and negative visual crops, forcing the student to rely on genuine visual evidence rather than shortcuts. Experiments on fine‑grained visual benchmarks show that CV‑OPD reduces shortcut learning and improves visual reasoning across existing VLMs.

By Haowei Wang, Hao Lin, Qi Zhu, Jiayi Ji, Deyi Ji, Liujuan Cao, Rongrong Ji
arXiv AI
Oct 2

LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation

LEGO-OPD introduces a factorized teacher composition for multimodal on‑policy distillation, combining a Language Expert and a Grounding Expert into a single teacher distribution. By treating the language expert as a prior over tokens and the grounding expert as a visual likelihood that updates this prior, the method decouples language reasoning from visual grounding. Adaptive calibration further adjusts the influence of visual evidence at each decoding prefix, preventing over‑ or under‑supervision. Experiments with Qwen3 models demonstrate that LEGO‑OPD outperforms both single‑ and multi‑teacher baselines on multimodal and text‑only reasoning tasks, improving visual perception while preserving language reasoning.

By Jaeyun Shin, Hangeol Chang, Jong Chul Ye
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
arXiv Computer Vision
Sep 30

VISTA: Internalizing Collective Visual Experience via On-Policy Distillation for Active Multimodal Agents

VISTA is a method for active multimodal agents that internalizes collective visual experience via on‑policy distillation. It turns observations from multiple rollouts of the same input into shared supervision, using Collective Visual Experience Distillation (CVED) to organize observations with context and Heterogeneity‑Aware Policy Improvement (HAPI) to reinforce successful trajectories and guide learning from unsuccessful ones. The approach lets an experience‑conditioned teacher evaluate a student’s partial responses, enabling discoveries from one trajectory to inform others without altering the student’s original history, and achieves superior performance on fine‑grained perception and general reasoning tasks compared to comparable agents.

By Zheng Jiang, Houde Qian, Yiming Chen, Ling Li, Chaoyang Li, Yueqi Li, Yuxuan Liu, Lifeng Sun
arXiv AI
Aug 17

Self-Supervised Visual On-Policy Distillation

arXiv:2608. 14144v1 Announce Type: cross Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest.

By Yijiang Li, Yijun Liang, Yunjie Tian, Bingyang Wang, Ke Zhang, Zhenfei Yin, Di Fu, Philip Torr, Nuno Vasconcelos