Author

Xuri Ge

h-index 13 View on Semantic Scholar

We have 5 of 56 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

I$^2$-KAN: Interpretable Intra- and Inter-Modal Multi-Pathway Representation Learning for Multimodal Sentiment Analysis

Multimodal sentiment analysis (MSA) aims to infer sentiment by integrating linguistic, acoustic, and visual information. However, many fusion methods integrate modality-specific representations and cross-modal interactions into joint representations, making it difficult to determine whether predictive utility arises fr...

Xiao-Ting Xie, Feng Qiao, Xian-Wei Zhang et al. · 0 citations

Preprint Sep 2026

Optimizing VLP-aligned Multimodal Intent Representation with Correct Visual Instantiation for Zero-Shot Composed Image Retrieval

ZS-CIR aims to retrieve a target image from a reference image and a modification text without paired supervision, typically by encoding composed queries as text-dominant representations within the image-text matching space of VLPs. However, queries reconstructed by visual pseudo-word learning or MLLM-based target reaso...

Xuri Ge, Chun-Hao Wang, Junchen Fu et al. · 0 citations

Preprint Sep 2026

Tracing Query Expansion Effects through Sparse Autoencoder Features

Analysis shows that effective QE induces layer-concentrated changes in sparse latents aligned with retrieval intent and entity attributes, rather than only perturbing final query embeddings, and suggests that SAEs can explain QE effects and offer a lightweight option for precise retrieval behavior modulation without qu...

Fang Dong, Wei-Ran Shi, Zhi-Wei Xu et al. · 0 citations

Review Sep 2026

A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources

This survey reviews core tasks, representative methods, and datasets in multimodal facial state analysis, focusing on facial expression recognition, AU detection, and face-based soft biometric estimation, and emphasizing the unique value of language in providing contextual semantics, enhancing reasoning, and generating...

Xuri Ge, Tian-Shuo Zhang, Ruihan Li et al. · 0 citations

#natural language process... Jan 2026

Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering

AdaRAS (Adaptive Reasoning Activation Steering), a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations during inference, enhancing incorrect reasoning traces while avoiding degradation on already-correct cases.

Fang Dong, Zu-Ming Yan, Xuri Ge et al. · arXiv.org · 5 citations