Xingqi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xingqi Wang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Jia Jia
Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China
2 shared publications - Xiaoyuan Yi
Microsoft Research Asia, Beijing, China
2 shared publications - Xing Xie
Microsoft Research Asia, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12304-12313
Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12304-12313
Open AccessSpecify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3558-3567
Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization
Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive content. Despite extensive research on Large Language Models (LLMs), the challenge of Text-to-Image (T2I) model alignment remains largely unexplored. Addressing this problem, we propose LiVO (Lightweight Value Optimization), a novel lightweight method for aligning T2I models with human values. LiVO only optimizes a plug-and-play value encoder to integrate a specified value principle with the input prompt, allowing the control of generated images over both semantics and values. Specifically, we design a diffusion model-tailored preference optimization loss, which theoretically approximates the Bradley-Terry model used in LLM alignment but provides a more flexible trade-off between image quality and value conformity. To optimize the value encoder, we also develop a framework to automatically construct a text-image preference dataset of 86k (prompt, aligned image, violating image, value principle) samples. Without updating most model parameters and through adaptive value selection from the input prompt, LiVO significantly reduces harmful outputs and achieves faster convergence, surpassing several strong baselines and taking an initial step towards ethically aligned T2I models. Warning: This paper involves descriptions and images depicting discriminatory, pornographic, bloody, and horrific scenes.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3558-3567
Open AccessEmbedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization
Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive content. Despite extensive research on Large Language Models (LLMs), the challenge of Text-to-Image (T2I) model alignment remains largely unexplored. Addressing this problem, we propose LiVO (Lightweight Value Optimization), a novel lightweight method for aligning T2I models with human values. LiVO only optimizes a plug-and-play value encoder to integrate a specified value principle with the input prompt, allowing the control of generated images over both semantics and values. Specifically, we design a diffusion model-tailored preference optimization loss, which theoretically approximates the Bradley-Terry model used in LLM alignment but provides a more flexible trade-off between image quality and value conformity. To optimize the value encoder, we also develop a framework to automatically construct a text-image preference dataset of 86k (prompt, aligned image, violating image, value principle) samples. Without updating most model parameters and through adaptive value selection from the input prompt, LiVO significantly reduces harmful outputs and achieves faster convergence, surpassing several strong baselines and taking an initial step towards ethically aligned T2I models. Warning: This paper involves descriptions and images depicting discriminatory, pornographic, bloody, and horrific scenes.