Xuzhao Shi

Xuzhao Shi

Auto-generated profile, based on publicly available information

Xuzhao Shi

Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
13 January 2026 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
TYTan Yue
Tan Yue
RMRui Mao
Rui Mao
XSXuzhao Shi
Xuzhao Shi
Erik CambriaErik Cambria
Erik Cambria
Multimodal sarcasm detection (MSD) aims to identify sarcastic expressions by integrating multimodal and contextual cues to capture cross-modal semantic inconsistencies. However, existing studies face challenges: fine-grained sarcastic cues are implicit and dispersed, large generative models suffer from gradient vanishing in classification tasks, and cross-domain generalization remains limited. To address these limitations, we propose InterARM, an interpretable affective reasoning model that introduces a structured sarcasm reasoning paradigm. Specifically, we introduce a three-stage training strategy based on curriculum learning, consisting of 1) sarcasm classification learning, 2) structured sarcasm reasoning learning, and 3) step-selective hierarchical reward reinforcement learning. The model generates reasoning chains across modalities to analyze sentiment polarity and semantic conflicts. We also construct the MSD-CoT dataset with 3,200 image-text pairs with 19,200 human-annotated reasoning steps. Experiments show that InterARM achieves superior performance on the in-domain and out-of-domain datasets, outperforming larger MLLMs such as Qwen2.5-VL-7B and GPT-5-mini while maintaining high interpretability and strong cross-domain generalization.

27 October 2025
Verified
Conference Paper
Open access
TYTan Yue
Tan Yue
XSXuzhao Shi
Xuzhao Shi
RMRui Mao
Rui Mao
ZSZilong Song
Zilong Song
ZHZonghai Hu
Zonghai Hu
DZDongyan Zhao
Dongyan Zhao

8 August 2026
Verified
Conference Paper
Open access
TYTan Yue
Tan Yue
RMRui Mao
Rui Mao
XSXuzhao Shi
Xuzhao Shi
ZSZilong Song
Zilong Song
SXSiyuan Xu
Siyuan Xu
DZDongyan Zhao
Dongyan Zhao

28 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
XSXuzhao Shi
Xuzhao Shi
YMYue Ming
Yue Ming
Multimodal sarcasm detection aims to identify conflicts betweenthe intended and literal meanings of image--text posts by combiningholistic semantics with sparse local cues. Local retrieval requires both correspondence weights and content features. We propose Role-Decoupled Cross-Modal Evidence Retrieval (RDCER) to assign separate representation sources to these two operations. RDCER uses a CLIP-anchored global branch for holistic prediction, while a local branch retrieves complementary token--patch evidence. Within local retrieval, CLIP-derived representations compute correspondence weights, whereas calibrated RoBERTa and ViT features supply the content aggregated by those weights. Inverse-Anchor Retrieval Enhancement (IARE) adjusts the query--key features using local--anchor dissimilarity. It adds anchor context to these features while leaving the calibrated value features unchanged. The local branch further aggregates bidirectional token--patch evidence into local logits that are combined with the global prediction through learnable additive fusion. Experiments on MMSD and MMSD2.0 show that RDCER achieves accuracies of 93.44\% and 86.26\%, respectively. These results support the proposed representation assignment within the evaluated global--local framework, where holistic semantics and retrieved token--patch content contribute complementary classification information.