跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-15AI 評分38

Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

AI 導讀

SCOPED 為不同能力分別訓練專家,透過獎勵引導反思提取技能,再以在策略蒸餾將程序知識整合至統一視覺語言模型。蒸餾時,技能只用於引導專家監督,不會提供給統一模型在推理時使用,以減少不同能力之間的幹擾。在八個多模態基準測試中,SCOPED 持續優於骨幹模型及混合能力強化學習方法。

正文

Published on Oct 15

Authors:

,

,

,

,

,

,

Abstract

SCOPED trains separate experts for distinct capabilities, extracts skills via reward-guided reflection, and distills procedural knowledge into a unified vision-language model without exposing explicit skills at inference, reducing cross-capability interference.

Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectives often introduces cross-capability gradient conflicts. Training experts independently mitigates this interference, but direct reward optimization may entangle specialized knowledge with reward-hacking biases. This paper proposes Skill-Decoupled On-Policy Expert Distillation (SCOPED), which trains capability-specific experts and extracts explicit skills through reward-guided reflection. During on-policy distillation, these skills guide expert supervision while remaining unavailable to the unified student, encouraging it to internalize procedural knowledge without explicit skills at inference time. Across eight multimodal benchmarks, SCOPED consistently outperforms the backbone and mixed-capability RL, demonstrating the effectiveness of skill-decoupled on-policy expert distillation for integrating independently acquired capabilities. Further analyses reveal interference during joint capability optimization and suggest that skill augmentation promotes more consistent expert trajectories, greater attention to task-relevant visual evidence, and better preservation of specialized expertise in the unified student. All code and data are available at https://github.com/NEUIR/SCOPED.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.22217

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.22217 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.22217 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.22217 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co