mlsanityData to 7 Oct 2026

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

arXiv 2504.09641 ↗First posted 13 Apr 2025cs.CVcited by 59

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
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.

Key facts. Cited by 59 papers in the map (data through 7 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.

Builds on

25 of 29 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model10 Apr
  2. 2025Video-R1: Reinforcing Video Reasoning in MLLMs27 Mar
  3. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL10 Mar
  4. 2025MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning10 Mar
  5. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar
  6. 2025R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model7 Mar
  7. 2025Visual-RFT: Visual Reinforcement Fine-Tuning3 Mar

Other references · 18

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  6. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,385
  7. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  8. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  9. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  10. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  11. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 1,086
  12. 2021NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actionscited by 735
6 more
  1. 2024LLaVA-Video: Video Instruction Tuning With Synthetic Datacited by 550
  2. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Modelscited by 539
  3. 2024ShareGPT4Video: Improving Video Understanding and Generation with Better Captionscited by 386
  4. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  5. 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Tokencited by 164
  6. 2025MMVU: Measuring Expert-Level Multi-Discipline Video Understandingcited by 131

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 39; 2026: 20.

59 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  2. 2025Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?cited by 107
  3. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  4. 2025VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuningcited by 86
  5. 2025DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPOcited by 57
  6. 2025ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understandingcited by 50
  7. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Modelscited by 43
  8. 2025Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidencecited by 43
  9. 2025EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversitycited by 41
  10. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 34
  11. 2025OctoNav: Towards Generalist Embodied Navigationcited by 33
  12. 2025VideoExplorer: Think With Videos For Agentic Long-Video Understandingcited by 29
38 more
  1. 2025Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoningcited by 29
  2. 2025Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thoughtcited by 23
  3. 2025Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Modelcited by 21
  4. 2025VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Managementcited by 19
  5. 2026VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twicecited by 19
  6. 2025SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimizationcited by 16
  7. 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMscited by 15
  8. 2025When Thinking Drifts: Evidential Grounding for Robust Video Reasoningcited by 15
  9. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  10. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 13
  11. 2025Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thoughtcited by 13
  12. 2025MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Groundingcited by 11
  13. 2025Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learningcited by 11
  14. 2025VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Taskscited by 10
  15. 2026EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Usecited by 10
  16. 2025SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapsecited by 9
  17. 2025CyberV: Cybernetics for Test-time Scaling in Video Understandingcited by 8
  18. 2025Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Modelscited by 8
  19. 2025VIDEOP2R: Video Understanding from Perception to Reasoningcited by 8
  20. 2025MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoningcited by 7
  21. 2025TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learningcited by 7
  22. 2025Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoningcited by 4
  23. 2025EgoExo-Con: Exploring View-Invariant Video Temporal Understandingcited by 4
  24. 2025ViSS-R1: Self-Supervised Reinforcement Video Reasoningcited by 4
  25. 2026MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correctioncited by 4
  26. 2025VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decompositioncited by 3
  27. 2026Omni-MMSI: Toward Identity-attributed Social Interaction Understandingcited by 3
  28. 2025Video Reasoning without Trainingcited by 2
  29. 2026Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videoscited by 2
  30. 2026Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMscited by 2
  31. 2025Constructing and Interpreting Digital Twin Representations for Visual Reasoning via Reinforcement Learningcited by 1
  32. 2026Weaver: End-to-End Agentic System Training for Video Interleaved Reasoningcited by 1
  33. 2026Balanced Thinking: Improving Chain of Thought Training in Vision Language Modelscited by 1
  34. 2026Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoningcited by 1
  35. 2026Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMscited by 1
  36. 2026I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoningcited by 1
  37. 2025ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Modelscited by 0
  38. 2025Decoupling Perception from Reasoning for Hallucination-Resistant Video Understandingcited by 0

50 most cited of 59 All 59 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
  2. 2025Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
  3. 2025ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small Models
  4. 2026How Far Are Video Models from True Multimodal Reasoning?
  5. 2025Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
  6. 2025Team of One: Cracking Complex Video QA with Model Synergy
  7. 2025OneThinker: All-in-one Reasoning Model for Image and Video
  8. 2026Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-Tuning