生成式人工智能的连续情感控制

该博士项目旨在解决让生成式人工智能能够在图像中像人类一样表达情感的问题。研究重点在于开发用于图像生成过程中的连续情感控制方法，运用创意人工智能与计算机视觉技术。申请者应具备Python、深度学习及用户研究方面的技能。

About the project How can AI create images that express emotion as naturally and flexibly as people do? This PhD will develop next-generation generative AI that enables continuous, reliable control of emotional expression in images. Building on our NeurIPS research, it combines creative AI, computer vision, and human-centred evaluation for broad real-world impact. Generative AI can produce remarkable images, yet it offers little reliable control over their emotional meaning. Current systems can follow prompts such as “happy” or “sad”, but cannot smoothly and consistently adjust emotion while preserving identity, image quality, and artistic style. This PhD will address this challenge by developing methods for continuous affective control in image-generation and editing models. Building on our NeurIPS 2026 paper, Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers, the project will investigate richer emotional representations and context-aware controls for people, animals, illustrations, artworks, and potentially video. The student will develop training-free and learning-based methods with diffusion and foundation models, evaluating them through computational measures and human-centred studies. The outcome will be generative AI that enables creators and users to shape emotional expression with greater precision, safety, and transparency. This matters for creative media, digital wellbeing, education, entertainment, and more natural human–AI interaction. The project sits within the Vision, Learning and Control (VLC) research group at the University of Southampton, offering an interdisciplinary environment and expertise in machine learning, computer vision, affective computing, and responsible AI. You will gain advanced skills in Python, deep learning, generative AI, experimental design, user studies, and open-source research. The School of Electronics and Computer Science is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.

入学要求 英国 2:1荣誉学位，或其国际等效学位，且所学专业为以下领域之一： 计算机科学 工程学 数学 或相关学科

资助：竞争性资助 学费与资助 我们为英国本土学生和国际学生提供多种资助机会。符合条件的学生可通过“地平线欧洲”学费减免，自动免除国际学生学费与英国本土学生学费之间的差额。 大学通过竞争性遴选授予的校长助学金，为遴选排名靠前的申请人支付国际学生学费与英国本土学生学费之间的差额。 本校各学院通过竞争性遴选提供的博士奖助金，通常为遴选排名靠前的申请人支付按英国本土学生标准收取的学费，并提供生活津贴。 资助采用滚动授予方式，因此请尽早申请，以尽可能增加进入资助评选的机会。 如需了解更多信息，请访问我们的研究生研究资助页面。

如何申请 您需： 选择课程类型（研究型）、2027/28学年、工程与物理科学学院 选择全日制或非全日制 搜索电子与电气工程博士项目（7092） 在申请表第2部分填写导师姓名 申请材料应包括： 研究提案 您的CV（个人简历） 2份学术推荐信 截至目前的学位课程成绩单和证书 英语语言资格证明（如适用）