Weiyu Xie

Weiyu Xie

Auto-generated profile, based on publicly available information

Weiyu Xie

Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
12 January 2021 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
SZSong-Hai Zhang
Song-Hai Zhang
SZShao-Kui Zhang
Shao-Kui Zhang
WXWei-Yu Xie
Wei-Yu Xie
CLCheng-Yang Luo
Cheng-Yang Luo
YYYong-Liang Yang
Yong-Liang Yang
HFHongbo Fu
Hongbo Fu
We present a framework for fast synthesizing indoor scenes, given a room geometry and a list of objects with learnt priors. Unlike existing data-driven solutions, which often learn priors by co-occurrence analysis and statistical model fitting, our method measures the strengths of spatial relations by tests for complete spatial randomness (CSR), and learns discrete priors based on samples with the ability to accurately represent exact layout patterns. With the learnt priors, our method achieves both acceleration and plausibility by partitioning the input objects into disjoint groups, followed by layout optimization using position-based dynamics (PBD) based on the Hausdorff metric. Experiments show that our framework is capable of measuring more reasonable relations among objects and simultaneously generating varied arrangements in seconds compared with the state-of-the-art works.

12 October 2025
Verified
Conference Paper
Open access
HCHongtao Chen
Hongtao Chen
WXWeiyu Xie
Weiyu Xie
BZBoxin Zhang
Boxin Zhang
JTJingqi Tang
Jingqi Tang
JWJiahao Wang
Jiahao Wang
MZMingxing Zhang
Mingxing Zhang

10 April 2024
Verified
Conference Paper
Open access
WXWeiyu Xie
Weiyu Xie
MZMingXing Zhang
MingXing Zhang
XLXia Liao
Xia Liao
KCKang Chen
Kang Chen
JJJinlei Jiang
Jinlei Jiang
YWYongWei Wu
YongWei Wu

2 April 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
JWJiahao Wang
Jiahao Wang
WXWeiyu Xie
Weiyu Xie
MZMingxing Zhang
Mingxing Zhang
BZBoxin Zhang
Boxin Zhang
JDJianwei Dong
Jianwei Dong
CJCongfeng JIANG
Congfeng JIANG
Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token. To mitigate this issue, existing solutions aim to reuse the preprocessed KVCache of each retrieved chunk to accelerate RAG. However, the lack of cross-chunk contextual information leads to a significant drop in generation quality, leaving the potential benefits of KVCache reuse largely unfulfilled. The challenge lies in how to reuse the precomputed KVCache chunk while preserving generation quality. We propose FusionRAG, a novel inference framework that optimizes both the preprocessing and reprocessing stages of RAG. In the offline preprocessing stage, we embed information from other related text chunks into each chunk, while in the online reprocessing stage, we recompute the KVCache for tokens that the model focuses on. As a result, we achieve a better trade-off between generation quality and efficiency. According to our experiments, FusionRAG significantly improves generation quality at the same recomputation ratio compared to previous state-of-the-art solutions. By recomputing fewer than 15% of the tokens, FusionRAG achieves up to 70% higher normalized-F1 scores than baselines and reduces TTFT by 2.66-9.39× compared to Full Attention.