6 papers
LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability
Xuan Xu, Zhongliang Yang, Haolun Li +5
Topic modeling aims to produce interpretable topic representations and topic--document correspondences from corpora, but classical neural topic models (NTMs) remain constrained by…
When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIP
Beilin Chu, Weike You, Mengtao Li +7
The rapid progress of GANs and Diffusion Models poses new challenges for detecting AI-generated images. Although CLIP-based detectors exhibit promising generalization, they often r…
FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error
Beilin Chu, Xuan Xu, Xin Wang +3
The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real image…
FinCPRG: A Bidirectional Generation Pipeline for Hierarchical Queries and Rich Relevance in Financial Chinese Passage Retrieval
Xuan Xu, Beilin Chu, Qinhong Lin +7
In recent years, large language models (LLMs) have demonstrated significant potential in constructing passage retrieval datasets. However, existing methods still face limitations i…
FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models
Xuan Xu, Fufang Wen, Beilin Chu +7
In natural language processing (NLP), the focus has shifted from encoder-only tiny language models like BERT to decoder-only large language models(LLMs) such as GPT-3. However, LLM…
Reduced Spatial Dependency for More General Video-level Deepfake Detection
Beilin Chu, Xuan Xu, Yufei Zhang +2
As one of the prominent AI-generated content, Deepfake has raised significant safety concerns. Although it has been demonstrated that temporal consistency cues offer better general…