Zhiyuan Wang

Zhiyuan Wang

Auto-generated profile, based on publicly available information

Zhiyuan Wang

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
15 November 2024 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
ZWZhiyuan Wang
Zhiyuan Wang
JDJinhao Duan
Jinhao Duan
CYChenxi Yuan
Chenxi Yuan
QCQingyu Chen
Qingyu Chen
TCTianlong Chen
Tianlong Chen
KXKaidi Xu
Kaidi Xu

28 October 2024
Verified
Conference Paper
Open access
JSJin Sun
Jin Sun
Xiaoshuang ShiXiaoshuang Shi
Xiaoshuang Shi
ZWZhiyuan Wang
Zhiyuan Wang
KXKaidi Xu
Kaidi Xu
HSHeng Tao Shen
Heng Tao Shen
XZXiaofeng Zhu
Xiaofeng Zhu
Modeling in Computer Vision has evolved to MLPs. Vision MLPs naturally lack local modeling capability, to which the simplest treatment is combined with convolutional layers. Convolution, famous for its sliding window scheme, also suffers from this scheme of redundancy and lower parallel computation. In this paper, we seek to dispense with the windowing scheme and introduce a more elaborate and parallelizable method to exploit locality. To this end, we propose a new MLP module, namely Shifted-Pillars-Concatenation (SPC), that consists of two steps of processes: (1) Pillars-Shift, which generates four neighboring maps by shifting the input image along four directions, and (2) Pillars-Concatenation, which applies linear transformations and concatenation on the maps to aggregate local features. SPC module offers superior local modeling power and performance gains, making it a promising alternative to the convolutional layer. Then, we build a pure-MLP architecture called Caterpillar by replacing the convolutional layer with the SPC module in a hybrid model of sMLPNet. Extensive experiments show Caterpillar's excellent performance on both small-scale and ImageNet-1k classification benchmarks, with remarkable scalability and transfer capability possessed as well. The code is available at https://github.com/sunjin19126/Caterpillar.

17 June 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YLYe Li
Ye Li
AHAnqi Hu
Anqi Hu
YYYuanchang Ye
Yuanchang Ye
STShiyan Tong
Shiyan Tong
ZWZhiyuan Wang
Zhiyuan Wang
BFBo Fu
Bo Fu
Large language models (LLMs) inherently operate over a large generation space, yet conventional usage typically reports the most likely generation (MLG) as a point prediction, which underestimates the model's capability: although the top-ranked response can be incorrect, valid answers may still exist within the broader output space and can potentially be discovered through repeated sampling. This observation motivates moving from point prediction to set-valued prediction, where the model produces a set of candidate responses rather than a single MLG. In this paper, we propose a principled framework for set-valued prediction, which provides feasibility-aware coverage guarantees. We show that, given the finite-sampling nature of LLM generation, coverage is not always achievable: even with multiple samplings, LLMs may fail to yield an acceptable response for certain questions within the sampled candidate set. To address this, we establish a minimum achievable risk level (MRL), below which statistical coverage guarantees cannot be satisfied. Building on this insight, we then develop a data-driven calibration procedure that constructs prediction sets from sampled responses by estimating a rigorous threshold, ensuring that the resulting set contains a correct answer with a desired probability whenever the target risk level is feasible. Extensive experiments on six language generation tasks with five LLMs demonstrate both the statistical validity and the predictive efficiency of our framework.