# TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding

arXiv: https://arxiv.org/abs/2508.04369 · HTML: https://mlsanity.com/paper/2508.04369/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding](https://mlsanity.com/paper/2407.15754/) (2024)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [LVBench: An Extreme Long Video Understanding Benchmark](https://mlsanity.com/paper/2406.08035/) (2024)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution](https://mlsanity.com/paper/2409.12961/) (2024)
- [Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward](https://mlsanity.com/paper/2404.01258/) (2024)
- [ST-LLM: Large Language Models Are Effective Temporal Learners](https://mlsanity.com/paper/2404.00308/) (2024)
- [M-LLM Based Video Frame Selection for Efficient Video Understanding](https://mlsanity.com/paper/2502.19680/) (2025)
- [T*: Re-thinking Temporal Search for Long-Form Video Understanding](https://mlsanity.com/paper/2504.02259/) (2025)
- [Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding](https://mlsanity.com/paper/2503.13139/) (2025)
- [Temporal Preference Optimization for Long-Form Video Understanding](https://mlsanity.com/paper/2501.13919/) (2025)
- [CoS: Chain-of-Shot Prompting for Long Video Understanding](https://mlsanity.com/paper/2502.06428/) (2025)
- [PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance](https://mlsanity.com/paper/2411.02327/) (2024)

## Built on by (most cited first, 25 of 25)

- [VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning](https://mlsanity.com/paper/2512.22315/) (2025)
- [Thinking in Streaming Video](https://mlsanity.com/paper/2603.12938/) (2026)
- [Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism](https://mlsanity.com/paper/2603.29252/) (2026)
- [TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2512.03963/) (2025)
- [MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding](https://mlsanity.com/paper/2602.22932/) (2026)
- [Video-Zero: Self-Evolution Video Understanding](https://mlsanity.com/paper/2605.14733/) (2026)
- [FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering](https://mlsanity.com/paper/2603.04349/) (2026)
- [When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition](https://mlsanity.com/paper/2603.16256/) (2026)
- [Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding](https://mlsanity.com/paper/2604.01002/) (2026)
- [Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding](https://mlsanity.com/paper/2512.00805/) (2025)
- [WAT: Online Video Understanding Needs Watching Before Thinking](https://mlsanity.com/paper/2603.13412/) (2026)
- [LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs](https://mlsanity.com/paper/2605.11477/) (2026)
- [Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding](https://mlsanity.com/paper/2607.28516/) (2026)
- [Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection](https://mlsanity.com/paper/2509.11058/) (2025)
- [MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction](https://mlsanity.com/paper/2601.03781/) (2026)
- [LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning](https://mlsanity.com/paper/2601.14594/) (2026)
- [Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning](https://mlsanity.com/paper/2603.26365/) (2026)
- [CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding](https://mlsanity.com/paper/2605.09223/) (2026)
- [STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation](https://mlsanity.com/paper/2607.02922/) (2026)
- [Gaussian Mixture Modeling for Event-Aware Visual Allocation in Long Video Understanding](https://mlsanity.com/paper/2607.12557/) (2026)
- [Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding](https://mlsanity.com/paper/2608.05780/) (2026)
- [LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents](https://mlsanity.com/paper/2608.07585/) (2026)
- [SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning](https://mlsanity.com/paper/2608.07959/) (2026)
- [Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs](https://mlsanity.com/paper/2609.10355/) (2026)
- [VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding](https://mlsanity.com/paper/2609.15606/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have demonstrated significant progress in vision-language tasks, yet they still face challenges when processing long-duration video inputs. The limitation arises from MLLMs' context limit and training costs, necessitating sparse frame sampling before feeding videos into MLLMs. However, building a trainable sampling method remains challenging due to the unsupervised and non-differentiable nature of sparse frame sampling in Video-MLLMs. To address these problems, we propose Temporal Sampling Policy Optimization (TSPO), advancing MLLMs' long-form video-language understanding via reinforcement learning. Specifically, we first propose a trainable event-aware temporal agent, which captures event-query correlation for performing probabilistic keyframe selection. Then, we propose the TSPO reinforcement learning paradigm, which models keyframe selection and language generation as a joint decision-making process, enabling end-to-end group relative optimization for the temporal sampling policy. Furthermore, we propose a dual-style long video training data construction pipeline, balancing comprehensive temporal understanding and key segment localization. Finally, we incorporate rule-based answering accuracy and temporal locating reward mechanisms to optimize the temporal sampling policy. Comprehensive experiments show that our TSPO achieves state-of-the-art performance across multiple long video understanding benchmarks, and shows transferable ability across different cutting-edge Video-MLLMs. Our code is available at https://github.com/Hui-design/TSPO