activity
20242026
most citedCrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation

2 citations · 2 across the 4 of their papers we have counts for

collaborators

6 papers

cs.AI2026

Multi-Dimensional Comparative Scale Construction for Efficient Personalized Subjective Judgment in High-Traffic Applications

Xianglong Shi, Shifeng Liu, Sirui Zhao +2

Subjective judgments are central to many high-traffic applications, but subjective intensity is difficult to quantify and perceptions vary substantially across individuals. To addr…

cs.AI2026

LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models

Xianglong Shi, Ruijie Yang, Sirui Zhao +4

Large language models increasingly serve as long-horizon assistants and agents, where they must both accumulate information across interactions and make the relevant parts availabl…

cs.LG2026

Intrinsic Lorentz Neural Network

Xianglong Shi, Ziheng Chen, Yunhan Jiang +1

Real-world data frequently exhibit latent hierarchical structures, which can be naturally represented by hyperbolic geometry. Although recent hyperbolic neural networks have demons…

cs.CV2025

LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension

Xianglong Shi, Silin Cheng, Sirui Zhao +4

Existing Weakly-Supervised Referring Expression Comprehension (WREC) methods, while effective, are fundamentally limited by a one-to-one mapping assumption, hindering their ability…

cs.CV2025★ 2 cited

CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation

Xianglong Shi, Yunhan Jiang, Xiaoheng Jiang +2

Crack Segmentation in industrial concrete surfaces is a challenging task because cracks usually exhibit intricate morphology with slender appearances. Traditional segmentation meth…

cs.CL2024

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration

Cheng Qian, Xianglong Shi, Shanshan Yao +6

We present a refined approach to biomedical question-answering (QA) services by integrating large language models (LLMs) with Multi-BERT configurations. By enhancing the ability to…