# Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback

arXiv: https://arxiv.org/abs/2402.03746 · HTML: https://mlsanity.com/paper/2402.03746/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [SALMON: Self-Alignment with Instructable Reward Models](https://mlsanity.com/paper/2310.05910/) (2023)
- [BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning](https://mlsanity.com/paper/2309.15785/) (2023)
- [Under the Surface: Tracking the Artifactuality of LLM-Generated Data](https://mlsanity.com/paper/2401.14698/) (2024)
- [VLM-Eval: A General Evaluation on Video Large Language Models](https://mlsanity.com/paper/2311.11865/) (2023)

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

- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward](https://mlsanity.com/paper/2404.01258/) (2024)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback](https://mlsanity.com/paper/2412.15838/) (2024)
- [Temporal Preference Optimization for Long-Form Video Understanding](https://mlsanity.com/paper/2501.13919/) (2025)
- [MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2512.06810/) (2025)
- [PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance](https://mlsanity.com/paper/2411.02327/) (2024)
- [VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models](https://mlsanity.com/paper/2504.13122/) (2025)
- [Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization](https://mlsanity.com/paper/2505.23525/) (2025)
- [ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding](https://mlsanity.com/paper/2506.01274/) (2025)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [Is Your Video Language Model a Reliable Judge?](https://mlsanity.com/paper/2503.05977/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation](https://mlsanity.com/paper/2407.07412/) (2024)
- [What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations](https://mlsanity.com/paper/2502.08279/) (2025)
- [SafeVid: Toward Safety Aligned Video Large Multimodal Models](https://mlsanity.com/paper/2505.11926/) (2025)
- [Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow](https://mlsanity.com/paper/2510.05836/) (2025)
- [VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment](https://mlsanity.com/paper/2504.14096/) (2025)
- [Reflection-Based Task Adaptation for Self-Improving VLA](https://mlsanity.com/paper/2510.12710/) (2025)
- [VideoSAVi: Self-Aligned Video Language Models without Human Supervision](https://mlsanity.com/paper/2412.00624/) (2024)
- [Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models](https://mlsanity.com/paper/2507.04976/) (2025)
- [Self-Improvement in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2510.02665/) (2025)
- [CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction](https://mlsanity.com/paper/2603.00610/) (2026)
- [MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning](https://mlsanity.com/paper/2603.25108/) (2026)
- [What Happens When: Learning Temporal Orders of Events in Videos](https://mlsanity.com/paper/2512.08979/) (2025)
- [VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation](https://mlsanity.com/paper/2604.02467/) (2026)
- [No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs](https://mlsanity.com/paper/2606.31933/) (2026)
- [Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation](https://mlsanity.com/paper/2504.18805/) (2025)
- [LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs](https://mlsanity.com/paper/2506.05260/) (2025)

## Abstract (arXiv)

Recent advancements in large language models have influenced the development of video large multimodal models (VLMMs). The previous approaches for VLMMs involved Supervised Fine-Tuning (SFT) with instruction-tuned datasets, integrating LLM with visual encoders, and adding additional learnable modules. Video and text multimodal alignment remains challenging, primarily due to the deficient volume and quality of multimodal instruction-tune data compared to text-only data. We present a novel alignment strategy that employs multimodal AI system to oversee itself called Reinforcement Learning from AI Feedback (RLAIF), providing self-preference feedback to refine itself and facilitating the alignment of video and text modalities. In specific, we propose context-aware reward modeling by providing detailed video descriptions as context during the generation of preference feedback in order to enrich the understanding of video content. Demonstrating enhanced performance across diverse video benchmarks, our multimodal RLAIF approach, VLM-RLAIF, outperforms existing approaches, including the SFT model. We commit to open-sourcing our code, models, and datasets to foster further research in this area.