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

• URL: http://arxiv.org/abs/2412.04814v3
• Date: Wed, 05 Mar 2025 02:43:42 GMT
• Title: LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
• Authors: Yibin Wang, Zhiyu Tan, Junyan Wang, Xiaomeng Yang, Cheng Jin, Hao Li,
• Abstract summary: This paper proposes LiFT, the first to leverage human feedback for T2V model alignment.<n>We first construct a Human Rating HRA, consisting of approximately 10k human annotations, each including a score and its corresponding rationale.<n>Based on this, we train a reward model LiFT-Critic to learn reward function effectively.<n> Lastly, we leverage the learned reward function to align the T2V model by maximizing the reward-weighted likelihood.
• Score: 15.11363628734519
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation [66.58048825989239]
  VideoPhy-2 is an action-centric dataset for evaluating physical commonsense in generated videos. We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos. Our findings reveal major shortcomings, with even the best model achieving only 22% joint performance.
  arXiv  Detail & Related papers  (2025-03-09T22:49:12Z)
• GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning [62.775721264492994]
  GRADEO is one of the first specifically designed video evaluation models. It grades AI-generated videos for explainable scores and assessments through multi-step reasoning. Experiments show that our method aligns better with human evaluations than existing methods.
  arXiv  Detail & Related papers  (2025-03-04T07:04:55Z)
• Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback [130.090296560882]
  We investigate the use of feedback to enhance the object dynamics in text-to-video models.<n>We show that our method can effectively optimize a wide variety of rewards, with binary AI feedback driving the most significant improvements in video quality for dynamic interactions.
  arXiv  Detail & Related papers  (2024-12-03T17:44:23Z)
• VideoSAVi: Self-Aligned Video Language Models without Human Supervision [0.6854849895338531]
  VideoSAVi is a self-training pipeline that enables Video-LLMs to reason over video content without external supervision. VideoSAVi achieves state-of-the-art performance on MVBench (74.0%) and delivers significant improvements. Our model-agnostic approach is computationally efficient, requiring only 32 frames.
  arXiv  Detail & Related papers  (2024-12-01T00:33:05Z)
• OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation [27.516068877910254]
  We introduce OpenHumanVid, a large-scale and high-quality human-centric video dataset.<n>Our findings yield two critical insights: First, the incorporation of a large-scale, high-quality dataset substantially enhances evaluation metrics for generated human videos.<n>Second, the effective alignment of text with human appearance, human motion, and facial motion is essential for producing high-quality video outputs.
  arXiv  Detail & Related papers  (2024-11-28T07:01:06Z)
• Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment [54.00254267259069]
  We establish the largest-scale Text-to-Video Quality Assessment DataBase (T2VQA-DB) to date. The dataset is composed of 10,000 videos generated by 9 different T2V models. We propose a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA)
  arXiv  Detail & Related papers  (2024-03-18T16:52:49Z)
• Towards A Better Metric for Text-to-Video Generation [102.16250512265995]
  Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. We introduce a novel evaluation pipeline, the Text-to-Video Score (T2VScore) This metric integrates two pivotal criteria: (1) Text-Video Alignment, which scrutinizes the fidelity of the video in representing the given text description, and (2) Video Quality, which evaluates the video's overall production caliber with a mixture of experts.
  arXiv  Detail & Related papers  (2024-01-15T15:42:39Z)
• UltraFeedback: Boosting Language Models with Scaled AI Feedback [99.4633351133207]
  We present textscUltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models.
  arXiv  Detail & Related papers  (2023-10-02T17:40:01Z)
• Aligning Text-to-Image Models using Human Feedback [104.76638092169604]
  Current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such models using human feedback. Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.
  arXiv  Detail & Related papers  (2023-02-23T17:34:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.