# VideoSSR: Video Self-Supervised Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.06281 · HTML: https://mlsanity.com/paper/2511.06281/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## 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/)

## Builds on (most cited first, 5 of 5)

- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models](https://mlsanity.com/paper/2407.12772/) (2024)
- [Self-supervised Video Representation Learning by Pace Prediction](https://mlsanity.com/paper/2008.05861/) (2020)
- [Cambrian-S: Towards Spatial Supersensing in Video](https://mlsanity.com/paper/2511.04670/) (2025)
- [Fostering Video Reasoning via Next-Event Prediction](https://mlsanity.com/paper/2505.22457/) (2025)

## Built on by (most cited first, 6 of 6)

- [DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models](https://mlsanity.com/paper/2512.24165/) (2025)
- [Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs](https://mlsanity.com/paper/2605.00814/) (2026)
- [MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction](https://mlsanity.com/paper/2601.03781/) (2026)
- [Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding](https://mlsanity.com/paper/2609.09300/) (2026)
- [VideoLatent: Video-Language Learning via Latent Self-Forcing](https://mlsanity.com/paper/2606.22870/) (2026)
- [EventLens: Event-Structure Reinforcement Learning for Video Understanding](https://mlsanity.com/paper/2610.16172/) (2026)

## Abstract (arXiv)

Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing video datasets, while the manual annotation of new, high-quality data remains prohibitively expensive. This work investigates a pivotal question: Can the rich, intrinsic information within videos be harnessed to self-generate high-quality, verifiable training data? To investigate this, we introduce three self-supervised pretext tasks: Anomaly Grounding, Object Counting, and Temporal Jigsaw. We construct the Video Intrinsic Understanding Benchmark (VIUBench) to validate their difficulty, revealing that current state-of-the-art MLLMs struggle significantly on these tasks. Building upon these pretext tasks, we develop the VideoSSR-30K dataset and propose VideoSSR, a novel video self-supervised reinforcement learning framework for RLVR. Extensive experiments across 17 benchmarks, spanning four major video domains (General Video QA, Long Video QA, Temporal Grounding, and Complex Reasoning), demonstrate that VideoSSR consistently enhances model performance, yielding an average improvement of over 5%. These results establish VideoSSR as a potent foundational framework for developing more advanced video understanding in MLLMs. The code is available at https://github.com/lcqysl/VideoSSR.