# Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation

arXiv: https://arxiv.org/abs/2602.02994 · HTML: https://mlsanity.com/paper/2602.02994/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 30 of 42)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [MiMo-V2-Flash Technical Report](https://mlsanity.com/paper/2601.02780/) (2026)
- [Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding](https://mlsanity.com/paper/2503.13377/) (2025)
- [MiMo-VL Technical Report](https://mlsanity.com/paper/2506.03569/) (2025)
- [TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning](https://mlsanity.com/paper/2410.19702/) (2024)
- [Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models](https://mlsanity.com/paper/2410.03290/) (2024)
- [HawkEye: Training Video-Text LLMs for Grounding Text in Videos](https://mlsanity.com/paper/2403.10228/) (2024)
- [Hierarchical Video-Moment Retrieval and Step-Captioning](https://mlsanity.com/paper/2303.16406/) (2023)
- [TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability](https://mlsanity.com/paper/2411.18211/) (2024)
- [Number it: Temporal Grounding Videos like Flipping Manga](https://mlsanity.com/paper/2411.10332/) (2024)
- [VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception](https://mlsanity.com/paper/2509.21100/) (2025)

## Built on by (most cited first, 30 of 36)

- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe](https://mlsanity.com/paper/2605.03677/) (2026)
- [Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation](https://mlsanity.com/paper/2606.02684/) (2026)
- [Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation](https://mlsanity.com/paper/2605.13643/) (2026)
- [SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling](https://mlsanity.com/paper/2606.09304/) (2026)
- [ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation](https://mlsanity.com/paper/2606.05718/) (2026)
- [V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning](https://mlsanity.com/paper/2606.25319/) (2026)
- [Weak-to-Strong On-Policy Distillation](https://mlsanity.com/paper/2607.26246/) (2026)
- [Latent On-Policy Self-Distillation](https://mlsanity.com/paper/2608.13040/) (2026)
- [A Formula-Driven Survey and Research Agenda for On-Policy Distillation](https://mlsanity.com/paper/2606.22793/) (2026)
- [When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation](https://mlsanity.com/paper/2608.03632/) (2026)
- [Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding](https://mlsanity.com/paper/2608.25356/) (2026)
- [Watch, Remember, Reason: Human-View Video Understanding with MLLMs](https://mlsanity.com/paper/2606.07433/) (2026)
- [Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs](https://mlsanity.com/paper/2608.20492/) (2026)
- [Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models](https://mlsanity.com/paper/2608.27065/) (2026)
- [On-Policy Adversarial Flow Distillation for Autoregressive Video Generation](https://mlsanity.com/paper/2605.26105/) (2026)
- [TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2607.17423/) (2026)
- [The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation](https://mlsanity.com/paper/2607.24720/) (2026)
- [Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation](https://mlsanity.com/paper/2608.11191/) (2026)
- [Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning](https://mlsanity.com/paper/2608.16316/) (2026)
- [StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding](https://mlsanity.com/paper/2608.16320/) (2026)
- [OPOD: On-Policy Omni Distillation](https://mlsanity.com/paper/2607.20918/) (2026)
- [Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding](https://mlsanity.com/paper/2609.09300/) (2026)
- [From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models](https://mlsanity.com/paper/2609.19553/) (2026)
- [Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension](https://mlsanity.com/paper/2602.13310/) (2026)
- [Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning](https://mlsanity.com/paper/2607.02963/) (2026)
- [TimePLE: Rethinking Temporal Representation for Video Temporal Grounding](https://mlsanity.com/paper/2607.23951/) (2026)
- [OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation](https://mlsanity.com/paper/2609.16459/) (2026)
- [Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation](https://mlsanity.com/paper/2609.34386/) (2026)
- [Counterfactual Attention Policy Distillation for Temporal Video Grounding](https://mlsanity.com/paper/2609.34581/) (2026)

## Abstract (arXiv)

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and substantial computational overhead. We propose Video-OPD, an efficient post-training framework for TVG inspired by recent advances in on-policy distillation. Video-OPD optimizes trajectories sampled directly from the current policy, thereby preserving alignment between training and inference distributions, while a frontier teacher supplies dense, token-level supervision via a reverse KL divergence objective. This formulation preserves the on-policy property critical for mitigating distributional shift, while converting sparse, episode-level feedback into fine-grained, step-wise learning signals. Building on Video-OPD, we introduce Teacher-Validated Disagreement Focusing (TVDF), a lightweight training curriculum that iteratively prioritizes trajectories that are both teacher-reliable and maximally informative for the student, thereby improving training efficiency. Empirical results demonstrate that Video-OPD consistently outperforms GRPO while achieving substantially faster convergence and lower computational cost, establishing on-policy distillation as an effective alternative to conventional reinforcement learning for TVG.