# LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment

arXiv: https://arxiv.org/abs/2412.04814 · HTML: https://mlsanity.com/paper/2412.04814/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 37 of its 39 references that are in the map.
- First posted on arXiv 6 Dec 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 37)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [Photorealistic Video Generation with Diffusion Models](https://mlsanity.com/paper/2312.06662/) (2023)
- [VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation](https://mlsanity.com/paper/2406.15252/) (2024)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [Video Diffusion Alignment via Reward Gradients](https://mlsanity.com/paper/2407.08737/) (2024)
- [Learning Multi-dimensional Human Preference for Text-to-Image Generation](https://mlsanity.com/paper/2405.14705/) (2024)
- [T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback](https://mlsanity.com/paper/2405.18750/) (2024)
- [InstructVideo: Instructing Video Diffusion Models with Human Feedback](https://mlsanity.com/paper/2312.12490/) (2023)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)

## Built on by (most cited first, 30 of 53)

- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [VideoScore2: Think before You Score in Generative Video Evaluation](https://mlsanity.com/paper/2509.22799/) (2025)
- [DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2506.03517/) (2025)
- [VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning](https://mlsanity.com/paper/2506.18564/) (2025)
- [UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation](https://mlsanity.com/paper/2510.18701/) (2025)
- [UniREditBench: A Unified Reasoning-based Image Editing Benchmark](https://mlsanity.com/paper/2511.01295/) (2025)
- [FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos](https://mlsanity.com/paper/2504.10358/) (2025)
- [HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment](https://mlsanity.com/paper/2503.23907/) (2025)
- [Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards](https://mlsanity.com/paper/2505.02686/) (2025)
- [IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios](https://mlsanity.com/paper/2505.20640/) (2025)
- [Unified Personalized Reward Model for Vision Generation](https://mlsanity.com/paper/2602.02380/) (2026)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning](https://mlsanity.com/paper/2510.10518/) (2025)
- [Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences](https://mlsanity.com/paper/2510.23451/) (2025)
- [Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning](https://mlsanity.com/paper/2510.14256/) (2025)
- [RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling](https://mlsanity.com/paper/2510.20206/) (2025)
- [Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning](https://mlsanity.com/paper/2601.04153/) (2026)
- [Aligning Anime Video Generation with Human Feedback](https://mlsanity.com/paper/2504.10044/) (2025)
- [VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation](https://mlsanity.com/paper/2505.23484/) (2025)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [RealDPO: Real or Not Real, that is the Preference](https://mlsanity.com/paper/2510.14955/) (2025)
- [PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models](https://mlsanity.com/paper/2512.01843/) (2025)
- [SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents](https://mlsanity.com/paper/2603.08403/) (2026)
- [MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning](https://mlsanity.com/paper/2603.25108/) (2026)
- [CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating](https://mlsanity.com/paper/2605.11723/) (2026)
- [VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation](https://mlsanity.com/paper/2608.18607/) (2026)
- [Q-Save: Towards Scoring and Attribution for Generated Video Evaluation](https://mlsanity.com/paper/2511.18825/) (2025)
- [SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models](https://mlsanity.com/paper/2512.22170/) (2025)

## Abstract (arXiv)

Recent advances in text-to-video (T2V) generative models have shown impressive capabilities. However, these models are still inadequate in aligning synthesized videos with human preferences (e.g., accurately reflecting text descriptions), which is particularly difficult to address, as human preferences are subjective and challenging to formalize as objective functions. Existing studies train video quality assessment models that rely on human-annotated ratings for video evaluation but overlook the reasoning behind evaluations, limiting their ability to capture nuanced human criteria. Moreover, aligning T2V model using video-based human feedback remains unexplored. Therefore, this paper proposes LiFT, the first method designed to leverage human feedback for T2V model alignment. Specifically, we first construct a Human Rating Annotation dataset, LiFT-HRA, consisting of approximately 10k human annotations, each including a score and its corresponding rationale. Based on this, we train a reward model LiFT-Critic to learn reward function effectively, which serves as a proxy for human judgment, measuring the alignment between given videos and human expectations. Lastly, we leverage the learned reward function to align the T2V model by maximizing the reward-weighted likelihood. As a case study, we apply our pipeline to CogVideoX-2B, showing that the fine-tuned model outperforms the CogVideoX-5B across all 16 metrics, highlighting the potential of human feedback in improving the alignment and quality of synthesized videos.