# TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

arXiv: https://arxiv.org/abs/2504.09641 · HTML: https://mlsanity.com/paper/2504.09641/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 13 Apr 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, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [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)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning](https://mlsanity.com/paper/2503.07365/) (2025)
- [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025)
- [LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token](https://mlsanity.com/paper/2501.03895/) (2025)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)
- [MMVU: Measuring Expert-Level Multi-Discipline Video Understanding](https://mlsanity.com/paper/2501.12380/) (2025)

## Built on by (most cited first, 30 of 62)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning](https://mlsanity.com/paper/2505.12434/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO](https://mlsanity.com/paper/2506.07464/) (2025)
- [ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding](https://mlsanity.com/paper/2506.01300/) (2025)
- [Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence](https://mlsanity.com/paper/2510.20579/) (2025)
- [Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2504.21277/) (2025)
- [EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity](https://mlsanity.com/paper/2507.21848/) (2025)
- [Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle](https://mlsanity.com/paper/2509.16679/) (2025)
- [OctoNav: Towards Generalist Embodied Navigation](https://mlsanity.com/paper/2506.09839/) (2025)
- [Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning](https://mlsanity.com/paper/2507.06485/) (2025)
- [VideoExplorer: Think With Videos For Agentic Long-Video Understanding](https://mlsanity.com/paper/2506.10821/) (2025)
- [Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought](https://mlsanity.com/paper/2505.19877/) (2025)
- [Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model](https://mlsanity.com/paper/2508.06206/) (2025)
- [VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice](https://mlsanity.com/paper/2601.05175/) (2026)
- [VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management](https://mlsanity.com/paper/2512.04540/) (2025)
- [SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization](https://mlsanity.com/paper/2506.01371/) (2025)
- [When Thinking Drifts: Evidential Grounding for Robust Video Reasoning](https://mlsanity.com/paper/2510.06077/) (2025)
- [TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs](https://mlsanity.com/paper/2509.18056/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2505.18536/) (2025)
- [Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought](https://mlsanity.com/paper/2506.08817/) (2025)
- [VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks](https://mlsanity.com/paper/2506.09079/) (2025)
- [MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding](https://mlsanity.com/paper/2505.20715/) (2025)
- [EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use](https://mlsanity.com/paper/2602.15329/) (2026)
- [Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning](https://mlsanity.com/paper/2507.00748/) (2025)
- [SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse](https://mlsanity.com/paper/2512.18671/) (2025)
- [CyberV: Cybernetics for Test-time Scaling in Video Understanding](https://mlsanity.com/paper/2506.07971/) (2025)
- [MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning](https://mlsanity.com/paper/2509.21113/) (2025)

## Abstract (arXiv)

Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as mathematics and code, and researchers generally choose large-scale models as the foundation. We argue that exploring small-scale models' reasoning capabilities remains valuable for researchers with limited computational resources. Moreover, enabling models to explain their reasoning processes on general question-answering datasets is equally meaningful. Therefore, we present the small-scale video reasoning model TinyLLaVA-Video-R1. Based on TinyLLaVA-Video, a traceably trained video understanding model with no more than 4B parameters, it not only demonstrates significantly improved reasoning and thinking capabilities after using reinforcement learning on general Video-QA datasets, but also exhibits the emergent characteristic of "aha moments". Furthermore, we share a series of experimental findings, aiming to provide practical insights for future exploration of video reasoning (thinking) abilities in small-scale models. It is available at https://github.com/ZhangXJ199/TinyLLaVA-Video-R1.