Skip to content
AI News HubLIVE
Original source2 min read

Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding

Summary

arXiv:2609.09300v1 Announce Type: new Abstract: Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning, which are difficult to jointly optimize within a single model. We introduce Video-MOPD-8B, an open-weight model dedicated to video understanding tasks. To fundamentally enhance its capabilities, we conduct targeted reinforcement learning (RL) optimization across three core domains: video temporal grounding (VTG), general video comprehension, and video STEM reasoning. We then unify their complementary capabilities via Multi-Teacher On-Policy Distillation (MOPD), which consolidates expert knowledge by supervising student-generated trajectories with routed teacher feedback. We further introduce Reliability-Aw…

SourcearXiv Computer VisionAuthor: Zhenxin Qin, Peng Shi, Cong Han, Yinlong Qian, Zequn Jie, Lin Ma
Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 8 Sep 2026]

Title:Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding

View a PDF of the paper titled Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding, by Zhenxin Qin and 5 other authors

View PDF HTML (experimental)

Abstract:Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning, which are difficult to jointly optimize within a single model. We introduce Video-MOPD-8B, an open-weight model dedicated to video understanding tasks. To fundamentally enhance its capabilities, we conduct targeted reinforcement learning (RL) optimization across three core domains: video temporal grounding (VTG), general video comprehension, and video STEM reasoning. We then unify their complementary capabilities via Multi-Teacher On-Policy Distillation (MOPD), which consolidates expert knowledge by supervising student-generated trajectories with routed teacher feedback. We further introduce Reliability-Aware Informative Sampling (RAIS), which selects examples with consistently reliable teacher supervision and large teacher-student performance gaps. Together, these components enable Video-MOPD-8B to achieve coordinated and comprehensive performance gains across diverse video understanding tasks. Extensive experiments on comprehensive benchmarks covering general video understanding, temporal grounding, video reasoning, and video STEM tasks demonstrate that Video-MOPD-8B achieves state-of-the-art performance among existing models at a comparable scale. The trained model weights are available at this https URL.

Comments: Technical report

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2609.09300 [cs.CV]

(or arXiv:2609.09300v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.09300

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zhenxin Qin [view email] [v1] Tue, 8 Sep 2026 18:00:22 UTC (1,708 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding, by Zhenxin Qin and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.09300v1 Announce Type: new Abstract: Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reas…

Highlights and analysis are generated automatically and may contain errors. Check the original source.