Yudong Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yudong Han has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Yun Ma
Peking University
8 shared publications - Weichen Bi
Peking University
5 shared publications - Deyu Tian
School of Computer Science, Peking University, Beijing, China
2 shared publications - Gang Huang
School of Computer Science, Peking University, Beijing, China
2 shared publications - Jiaqi Du
Peking University
2 shared publications - Mugeng Liu
School of Computer Science, Peking University, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2825-2834
WebSplatter: Efficient and Faithful In-Browser 3D Gaussian Splatting across Devices via WebGPU
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2825-2834
Open AccessWebSplatter: Efficient and Faithful In-Browser 3D Gaussian Splatting across Devices via WebGPU
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1609-1621
Characterizing GPU-accelerated Web Applications in Browsers
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1609-1621
Open AccessCharacterizing GPU-accelerated Web Applications in Browsers
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2483-2492
WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browsers
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2483-2492
Open AccessWebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browsers
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 751-762
GL2GPU: Accelerating WebGL Applications via Dynamic API Translation to WebGPU
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 751-762
Open AccessGL2GPU: Accelerating WebGL Applications via Dynamic API Translation to WebGPU
- 27 November 2024
- Published by Springer Nature
- p. 301-312
Web-Based AI Assistant for Medical Imaging: A Case Study on Predicting Spontaneous Preterm Birth via Ultrasound Images
- 27 November 2024
- Published by Springer Nature
- p. 301-312
Web-Based AI Assistant for Medical Imaging: A Case Study on Predicting Spontaneous Preterm Birth via Ultrasound Images
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 36 (2) , 212-225
DegaFL: Decentralized Gradient Aggregation for Cross-Silo Federated Learning
Federated learning (FL) is an emerging promising paradigm of privacy-preserving machine learning (ML). An important type of FL is cross-silo FL, which enables a moderate number of organizations to cooperatively train a shared model by keeping confidential data locally and aggregating gradients on a central parameter server. However, the central server may be vulnerable to malicious attacks or software failures in practice. To address this issue, in this paper, we propose DegaFL , a novel decentralized gradient aggregation approach for cross-silo FL. DegaFL eliminates the central server by aggregating gradients on each participant, and maintains and synchronizes gradients of only the current training round. Besides, we propose AdaAgg to adaptively aggregate correct gradients from honest nodes and use HotStuff to ensure the consistency of the training round number and gradients among all nodes. Experimental results show that DegaFL defends against common threat models with minimal accuracy loss, and achieves up to $50\times$ reduction in storage overhead and up to $13\times$ reduction in network overhead, compared to state-of-the-art decentralized FL approaches.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 36 (2) , 212-225
DegaFL: Decentralized Gradient Aggregation for Cross-Silo Federated Learning
Federated learning (FL) is an emerging promising paradigm of privacy-preserving machine learning (ML). An important type of FL is cross-silo FL, which enables a moderate number of organizations to cooperatively train a shared model by keeping confidential data locally and aggregating gradients on a central parameter server. However, the central server may be vulnerable to malicious attacks or software failures in practice. To address this issue, in this paper, we propose DegaFL , a novel decentralized gradient aggregation approach for cross-silo FL. DegaFL eliminates the central server by aggregating gradients on each participant, and maintains and synchronizes gradients of only the current training round. Besides, we propose AdaAgg to adaptively aggregate correct gradients from honest nodes and use HotStuff to ensure the consistency of the training round number and gradients among all nodes. Experimental results show that DegaFL defends against common threat models with minimal accuracy loss, and achieves up to $50\times$ reduction in storage overhead and up to $13\times$ reduction in network overhead, compared to state-of-the-art decentralized FL approaches.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2890-2901
FusionRender: Harnessing WebGPU's Power for Enhanced Graphics Performance on Web Browsers
Graphics rendering on web browsers serves as the foundation for numerous web applications. Compared with the widely employed WebGL, the next-generation web graphics API, WebGPU, demonstrates an enhanced capacity to adapt to modern GPU features, boasting more significant potential. However, our experiment shows that the performance of current graphics rendering frameworks based on WebGPU lags behind those built on WebGL. Such discrepancy primarily arises from an incomplete alignment with WebGPU's distinctive features. The individual rendering of each graphic leads to redundant communication between the CPU and GPU. To enhance the graphics performance on the web, we introduce the FusionRender to harness the power of WebGPU. To mitigate redundant communication, FusionRender assigns a unique signature to each object and employs these signatures for grouping, enabling the consolidation of graphics rendering whenever possible. In simulated experiments involving the rendering of multiple objects, FusionRender improves the rendering performance by 29.3%-122.1% compared with the existing optimal baseline. In real cases with more complex features, performance improvement ranges from 9.4% to 39.7%. Additionally, FusionRender exhibits robust performance enhancement across various devices and browsers.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2890-2901
Open AccessFusionRender: Harnessing WebGPU's Power for Enhanced Graphics Performance on Web Browsers
Graphics rendering on web browsers serves as the foundation for numerous web applications. Compared with the widely employed WebGL, the next-generation web graphics API, WebGPU, demonstrates an enhanced capacity to adapt to modern GPU features, boasting more significant potential. However, our experiment shows that the performance of current graphics rendering frameworks based on WebGPU lags behind those built on WebGL. Such discrepancy primarily arises from an incomplete alignment with WebGPU's distinctive features. The individual rendering of each graphic leads to redundant communication between the CPU and GPU. To enhance the graphics performance on the web, we introduce the FusionRender to harness the power of WebGPU. To mitigate redundant communication, FusionRender assigns a unique signature to each object and employs these signatures for grouping, enabling the consolidation of graphics rendering whenever possible. In simulated experiments involving the rendering of multiple objects, FusionRender improves the rendering performance by 29.3%-122.1% compared with the existing optimal baseline. In real cases with more complex features, performance improvement ranges from 9.4% to 39.7%. Additionally, FusionRender exhibits robust performance enhancement across various devices and browsers.
- Open Access
- 15 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 113-117
TrickyBugs: A Dataset of Corner-case Bugs in Plausible Programs
We call a program that passes existing tests but still contains bugs as a buggy plausible program. Bugs in such a program can bypass the testing environment and enter the production environment, causing unpredictable consequences. Therefore, discovering and fixing such bugs is a fundamental and critical problem. However, no existing bug dataset is purposed to collect this kind of bug, posing significant obstacles to relevant research. To address this gap, we introduce TrickyBugs, a bug dataset with 3,043 buggy plausible programs sourced from human-written submissions of 324 real-world competition coding tasks. We identified the buggy plausible programs from approximately 400,000 submissions, and all the bugs in TrickyBugs were not previously detected. We hope that TrickyBugs can effectively facilitate research in the fields of automated program repair, fault localization, test generation, and test adequacy.
- 15 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 113-117
Open AccessTrickyBugs: A Dataset of Corner-case Bugs in Plausible Programs
We call a program that passes existing tests but still contains bugs as a buggy plausible program. Bugs in such a program can bypass the testing environment and enter the production environment, causing unpredictable consequences. Therefore, discovering and fixing such bugs is a fundamental and critical problem. However, no existing bug dataset is purposed to collect this kind of bug, posing significant obstacles to relevant research. To address this gap, we introduce TrickyBugs, a bug dataset with 3,043 buggy plausible programs sourced from human-written submissions of 324 real-world competition coding tasks. We identified the buggy plausible programs from approximately 400,000 submissions, and all the bugs in TrickyBugs were not previously detected. We hope that TrickyBugs can effectively facilitate research in the fields of automated program repair, fault localization, test generation, and test adequacy.