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

• URL: http://arxiv.org/abs/2609.09300v1
• Date: Tue, 08 Sep 2026 18:00:22 GMT
• Title: Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding
• Abstract summary: Video understanding demands a convergence of complementary capabilities across perception, temporal understanding, and complex reasoning.<n>We introduce Video-MOPD-8B, an open-weight model dedicated to video understanding tasks.<n>We conduct targeted reinforcement learning (RL) optimization across three core domains: video temporal grounding (VTG), general video comprehension, and video STEM reasoning.
• Score: 32.55965761036089
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 https://huggingface.co/LandH/Video-MOPD-8B.

Related papers

• VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding [73.10050069618302]
  VideoGAIA is an agentic video understanding benchmark for general artificial intelligence assistants.<n>VideoGAIA contains 271 model-human co-designed tasks covering diverse and complex real-world scenarios.<n>All evaluated MLLMs, including frontier models such as GPT-5.5 and Kimi-K3, achieve less than 60% accuracy on VideoGAIA.
  arXiv  Detail & Related papers  (2026-08-12T03:24:44Z)
• EasyVideoR1: Easier RL for Video Understanding [51.760544033045726]
  Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models.<n>EasyVideoR1 is a complete and efficient reinforcement learning framework specifically designed for training large vision-language models on video understanding tasks.
  arXiv  Detail & Related papers  (2026-04-18T07:56:32Z)
• Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models [78.32948112203228]
  Video understanding represents the most challenging frontier in computer vision.<n>Recent emergence of Video-Large Multitemporal Models has demonstrated remarkable capabilities in video understanding tasks.<n>Survey aims to provide researchers and practitioners with a unified framework for advancing Video-LMM capabilities.
  arXiv  Detail & Related papers  (2025-10-06T17:10:44Z)
• ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts [56.75723197779384]
  ARC-Hunyuan-Video is a multimodal model that processes visual, audio, and textual signals end-to-end for structured comprehension.<n>Our model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning.
  arXiv  Detail & Related papers  (2025-07-28T15:52:36Z)
• VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding [45.83476222676765]
  We propose Instructed Temporal Grounding for Videos (VideoITG), featuring customized frame sampling aligned with user instructions.<n>The core of VideoITG is the VidThinker pipeline, an automated annotation framework that explicitly mimics the human annotation process.<n>We show that VideoITG achieves consistent performance improvements across multiple multimodal video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-07-17T17:59:59Z)
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding [23.96372422130216]
  Video-based Large Language Models (VideoVid-LLMs) have witnessed substantial advancements in recent years.<n>They struggle with fine-grained understanding, particularly in aspects such as visual dynamics and video details inquiries.<n>To tackle these shortcomings, we find that fine-tuning Video-LLMs on self-supervised fragment tasks greatly improve their fine-grained video understanding abilities.
  arXiv  Detail & Related papers  (2025-04-10T13:40:34Z)
• STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
  Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks.<n>Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events.<n>We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
  arXiv  Detail & Related papers  (2024-11-29T11:54:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.