This paper presents an exploration of preference learning in text-to-motion generation. We find that current improvements in text-to-motion generation still rely on datasets requiring expert labelers with motion capture systems. Instead, learning from human preference data does not require motion capture systems; a labeler with no expertise simply compares two generated motions. This is particularly efficient because evaluating the model's output is easier than gathering the motion that performs a desired task (e.g. backflip). To pioneer the exploration of this paradigm, we annotate 3,528 preference pairs generated by MotionGPT, marking the first effort to investigate various algorithms for learning from preference data. In particular, our exploration highlights important design choices when using preference data. Additionally, our experimental results show that preference learning has the potential to greatly improve current text-to-motion generative models. Our code and dataset are publicly available at https://github.com/THU-LYJ-Lab/InstructMotion}{https://github.com/THU-LYJ-Lab/InstructMotion to further facilitate research in this area.
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（人工智能向量研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）；Kling Team, Kuaishou Technology（快手科技 Kling 团队）；NSERC CRC Chair（加拿大NSERC CRC主席）
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）；Centre for Perceptual and Interactive Intelligence（感知与交互智能研究中心）
Instant Preference Alignment for Text-to-Image Diffusion Models
New Laboratory of Pattern Recognition, CASIA（模式识别新实验室，中国科学院自动化研究所）；The Hong Kong University of Science and Technology（香港科技大学）；Nanjing university（南京大学）；Academy of Broadcasting Science, NRTA（广播科学研究院，国家广播电视总局）
Human Preference Score: Better Aligning Text-to-Image Models with Human Preference
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）；Centre for Perceptual and Interactive Intelligence (CPII)（感知与交互智能中心（CPII））；Shanghai AI Laboratory（上海人工智能实验室）
FERGI: Automatic Scoring of User Preferences for Text-to-Image Generation from Spontaneous Facial Expression Reaction
Neurosciences Graduate Program, University of California San Diego（加州大学圣地亚哥分校神经科学研究生项目）；Department of Computer Science and Engineering, University of California San Diego（加州大学圣地亚哥分校计算机科学与工程系）；Department of Cognitive Science, University of California San Diego（加州大学圣地亚哥分校认知科学系）；Halıcıoğlu Data Science Institute, University of California San Diego（加州大学圣地亚哥分校Halıcıoğlu数据科学研究所）
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理关键实验室，复旦大学计算机学院）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）
Exploring Applications of State Space Models and Advanced Training Techniques in Sequential Recommendations: A Comparative Study on Efficiency and Performance
VLP: Vision-Language Preference Learning for Embodied Manipulation
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院）；King’s College London（伦敦国王学院）
$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；The Hong Kong University of Science and Technology（香港科技大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）
Preference Discerning with LLM-Enhanced Generative Retrieval
ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz（ELLIS单位、LIT人工智能实验室、机器学习研究所、JKU林茨）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；AI at Meta（Meta人工智能）
