Yuyao Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuyao Yan has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Kaizhu Huang
Duke Kunshan University, Kunshan, China
13 shared publications - Chaolong Yang
Xi’an Jiaotong-Liverpool University, Suzhou, China, University of Liverpool, Liverpool, United Kingdom, and Duke Kunshan University, Kunshan, China
7 shared publications - Weiguang Zhao
University of Liverpool, Liverpool, United Kingdom
7 shared publications - Xi Yang
Xi’an Jiaotong-Liverpool University, Suzhou, China
7 shared publications - Rui Zhang
Xi’an Jiaotong-Liverpool University, Suzhou, China
5 shared publications - Amir Hussain
School of Computing, Edinburgh Napier University, Scotland, UK
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17238-17240
KD-Avatar: A Real-Time Controllable Cross-Language Meeting Avatar System
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17238-17240
Open AccessKD-Avatar: A Real-Time Controllable Cross-Language Meeting Avatar System
- 6 October 2026
- Published by Springer Nature
- p. 483-495
A Light-Attention CNN–GRU Framework for Long-Horizon UAV Flight
- 6 October 2026
- Published by Springer Nature
- p. 483-495
A Light-Attention CNN–GRU Framework for Long-Horizon UAV Flight
- 6 October 2026
- Published by Springer Nature
- p. 541-548
Learning Text Prompts for Robust Real-World PCB Anomaly Detection
- 6 October 2026
- Published by Springer Nature
- p. 541-548
Learning Text Prompts for Robust Real-World PCB Anomaly Detection
- 6 October 2026
- Published by Springer Nature
- p. 307-320
EmoSound: A Multimodal AI Agent Framework for Emotion-Aware Audio Accompaniment of Emoticons
- 6 October 2026
- Published by Springer Nature
- p. 307-320
EmoSound: A Multimodal AI Agent Framework for Emotion-Aware Audio Accompaniment of Emoticons
- Open Access
- 1 May 2026
- Published by Elsevier in SSRN Electronic Journal
Towards Cross-Device Robotic Grasping Policy in 3D Open World
Given the diversity of devices and the product upgrades, cross-device research has become an urgent issue that needs to be tackled. To this end, we pioneer in probing the cross-device (cameras & robotics) grasping policy in the 3D open world. Specifically, we construct two real-world grasping setups, employing robotic arms and cameras from completely different manufacturers. To minimize domain differences in point clouds from diverse cameras, we adopt clustering methods to generate 3D object proposals. However, existing clustering methods are limited to closed-set scenarios, which confines the robotic graspable object categories and ossifies the deployment scenarios. To extend these methods to open-world settings, we introduce the SSGC-Seg module that enables category-agnostic 3D object detection. The proposed module transforms the original multi-class semantic information into binary semantic cues—foreground and background by analyzing the SoftMax value of each point, and then clusters the foreground points based on geometric information to form initial object proposals. Furthermore, ScoreNet++ is designed to score each detection result, and the robotic arm prioritizes grasping the object with the highest confidence score. Experiments on two different types of setups highlight the effectiveness and robustness of our policy for cross-device robotics grasping research.
- 1 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTowards Cross-Device Robotic Grasping Policy in 3D Open World
Given the diversity of devices and the product upgrades, cross-device research has become an urgent issue that needs to be tackled. To this end, we pioneer in probing the cross-device (cameras & robotics) grasping policy in the 3D open world. Specifically, we construct two real-world grasping setups, employing robotic arms and cameras from completely different manufacturers. To minimize domain differences in point clouds from diverse cameras, we adopt clustering methods to generate 3D object proposals. However, existing clustering methods are limited to closed-set scenarios, which confines the robotic graspable object categories and ossifies the deployment scenarios. To extend these methods to open-world settings, we introduce the SSGC-Seg module that enables category-agnostic 3D object detection. The proposed module transforms the original multi-class semantic information into binary semantic cues—foreground and background by analyzing the SoftMax value of each point, and then clusters the foreground points based on geometric information to form initial object proposals. Furthermore, ScoreNet++ is designed to score each detection result, and the robotic arm prioritizes grasping the object with the highest confidence score. Experiments on two different types of setups highlight the effectiveness and robustness of our policy for cross-device robotics grasping research.
- 6 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 111
Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait
- 6 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 111
Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait
- 12 January 2026
- Published by Springer Nature
- p. 562-576
Stock Price Prediction with Attention-Based Framework by Integrating LLM-Generated Features
- 12 January 2026
- Published by Springer Nature
- p. 562-576
Stock Price Prediction with Attention-Based Framework by Integrating LLM-Generated Features
- 12 January 2026
- Published by Springer Nature
- p. 547-561
Entropy-Guided Distillation for Medical Image Segmentation Under Missing Modalities
- 12 January 2026
- Published by Springer Nature
- p. 547-561
Entropy-Guided Distillation for Medical Image Segmentation Under Missing Modalities
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13486-13488
KDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13486-13488
Open AccessKDTalker++: Controllable Talking Portrait Generation with Audio, Text, and Expression Editing
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4147-4155
Towards Training-Free Open-World Classification with 3D Generative Models
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4147-4155
Open AccessTowards Training-Free Open-World Classification with 3D Generative Models