Heng Xie

Heng Xie

Auto-generated profile, based on publicly available information

Heng Xie

Beijing Institute of Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
27 October 2025
Verified
Conference Paper
Open access
CCCong Cai
Cong Cai
SLShan Liang
Shan Liang
XLXuefei Liu
Xuefei Liu
KZKang Zhu
Kang Zhu
ZWZhengqi Wen
Zhengqi Wen
YLYongwei Li
Yongwei Li

29 October 2023
Verified
Conference Paper
Open access
HXHeng Xie
Heng Xie
JCJizhou Cui
Jizhou Cui
YCYuhang Cao
Yuhang Cao
JCJunjie Chen
Junjie Chen
TJTao Jianhua
Tao Jianhua
YLYongwei Li
Yongwei Li
Sentiment analysis plays a crucial role in interpreting human interactions across different modalities. This paper addresses the Cross-Cultural Multilingual Humour Detection Sub-Challenge in the MuSe 2023 Multi-modal Sentiment Analysis Challenge, which aims to identify humor instances in cross-cultural situations using multimodal data. In this paper, we explore the unique window length processing of audio data to more accurately and fully capture humor information. Furthermore, we employ a data augmentation technique for text to bridge the gap between the train set and the test set. This augmentation involves converting German and English samples in the database to each other, as well as translating both languages into Chinese. These techniques aim to enhance the model's generalization across different languages and alleviate the scarcity of humor samples. For multimodal fusion, we use the late fusion technique applied to different Gated Recurrent Unit (GRU) models with modality-specific weights obtained through gradient descent. Experimental results demonstrate the effectiveness of our approach, achieving an Area Under the Curve (AUC) score of 0.872 on the MuSe-Humor test set. This performance ranked second place in the sub-challenge.

26 October 2025
Verified
Conference Paper
Open access
JCJizhou Cui
Jizhou Cui
HXHanzhe Xu
Hanzhe Xu
XLXuefei Liu
Xuefei Liu
ZLZheng Lian
Zheng Lian
ZWZhengqi Wen
Zhengqi Wen
TJTao Jianhua
Tao Jianhua

22 April 2026 in Axioms
Verified
Journal Article
Open access
PDF file
ZCZiyi Cao
Ziyi Cao
JZJingbin Zhang
Jingbin Zhang
SWShuai Wang
Shuai Wang
SLShaobo Li
Shaobo Li
BLBingquan Liu
Bingquan Liu
HXHeng Xie
Heng Xie
Reusing separate, pre-filled Key-Value (KV) Caches for multiple contexts has become a common practice in handling multi-context scenarios with Large Language Models. However, this leads to a lack of cross-attention mechanisms between contexts. To address this, we propose CatLLM, the first method that concatenates multiple contexts across requests offline to compensate for this deficiency. Specifically, during offline processing, CatLLM identifies contexts that severely lack cross-attention by incorporating the weighted inner products of Q and K vectors from tokens in an un-concatenated context into an equivalently transformed weighted formulation for concatenated Q and K inner products. This yields a weighting wiA+B corresponding to the output vector difference, which can then be used to identify contexts with severe cross-attention deficiencies and concatenate them into a single context for KV Cache computation. Experimental results show that, compared to the baseline of separate caching (i.e., no concatenation), fully concatenating all contexts improves the F1 score by 6%. Meanwhile, the proposed method reduces the number of contexts requiring caching from 10 to 7 while achieving a 3% F1 score, thereby maximizing performance improvement while minimizing the degree of context compression.