Yunheng Shen

Yunheng Shen

Auto-generated profile, based on publicly available information

Yunheng Shen

Tsinghua University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 June 2024
Verified
Conference Paper
Open access
ZWZixiao Wang
Zixiao Wang
YSYunheng Shen
Yunheng Shen
XYXufeng Yao
Xufeng Yao
WZWenqian Zhao
Wenqian Zhao
YBYang Bai
Yang Bai
BYBei Yu
Bei Yu
Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention. In this paper, we propose ChatPattern, a novel Large-Language-Model (LLM) powered framework for flexible pattern customization. ChatPattern utilizes a two-part system featuring an expert LLM agent and a highly controllable layout pattern generator. The LLM agent can interpret natural language requirements and operate design tools to meet specified needs, while the generator excels in conditional layout generation, pattern modification, and memory-friendly patterns extension. Experiments on challenging pattern generation setting shows the ability of ChatPattern to synthesize high-quality large-scale patterns.

22 September 2022 in ACM Transactions on Intelligent Systems and Technology
Verified
Journal Article
Open access
JOJinxiang Ou
Jinxiang Ou
YSYunheng Shen
Yunheng Shen
FWFeng Wang
Feng Wang
QLQiao Liu
Qiao Liu
XZXuegong Zhang
Xuegong Zhang
HLHai-Rong Lv
Hai-Rong Lv
Federated learning (FL) is a privacy-preserving paradigm for multi-institutional collaborations, where the aggregation is an essential procedure after training on the local datasets. Conventional aggregation algorithms often apply a weighted averaging of the updates generated from distributed machines to update the global model. However, while the data distributions are non-IID, the large discrepancy between the local updates might lead to a poor averaged result and a lower convergence speed, i.e., more iterations required to achieve a certain performance. To solve this problem, this article proposes a novel method named AggEnhance for enhancing the aggregation, where we synthesize a group of reliable samples from the local models and tune the aggregated result on them. These samples, named class interior points (CIPs) in this work, bound the relevant decision boundaries that ensure the performance of aggregated result. To the best of our knowledge, this is the first work to explicitly design an enhancing method for the aggregation in prevailing FL pipelines. A series of experiments on real data demonstrate that our method has noticeable improvements of the convergence in non-IID scenarios. In particular, our approach reduces the iterations by 31.87% on average for the CIFAR10 dataset and 43.90% for the PASCAL VOC dataset. Since our method does not modify other procedures of FL pipelines, it is easy to apply to most existing FL frameworks. Furthermore, it does not require additional data transmitted from the local clients to the global server, thus holding the same security level as the original FL algorithms.

29 August 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
JSJiarui Song
Jiarui Song
YSYunheng Shen
Yunheng Shen
CHChengbin Hou
Chengbin Hou
PWPengyu Wang
Pengyu Wang
JWJinbao Wang
Jinbao Wang
HLHai-Rong Lv
Hai-Rong Lv

1 January 2026 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
YSYunheng Shen
Yunheng Shen
LZLing Zheng
Ling Zheng
JZJun Zhong
Jun Zhong
CMChong Miao
Chong Miao
HLHai-Rong Lv
Hai-Rong Lv
YYYang Yang
Yang Yang

12 May 2025 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
ZWZixiao Wang
Zixiao Wang
WZWenqian Zhao
Wenqian Zhao
YSYunheng Shen
Yunheng Shen
YBYang Bai
Yang Bai
GCGuojin Chen
Guojin Chen
BYBei Yu
Bei Yu
Recent advancements in layout pattern generation have been dominated by deep generative models. However, relying solely on neural networks for legality guarantees raises concerns in many practical applications. In this article, we present $\textsf {DiffPattern}$ -Flex, a novel approach designed to generate reliable layout patterns efficiently. $\textsf {DiffPattern}$ -Flex incorporates a new method for generating diverse topologies using a discrete diffusion model while maintaining a lossless and compute-efficient layout representation. To ensure legal pattern generation, we employ an optimization-based, glass-box pattern assessment process based on specific design rules. Furthermore, fast sampling and efficient legalization technologies are employed to accelerate the generation process. Experimental results across various benchmarks demonstrate that $\textsf {DiffPattern}$ -Flex significantly outperforms existing methods and excels at producing reliable layout patterns.