5 papers
Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
Zhuchenyang Liu, Ziyu Hu, Yao Zhang +1
Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index storage overhead. Existing training-free…
Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization
Hao Li, Yubin Xiao, Ke Liang +4
Single Domain Generalization (SDG) aims to train models that maintain consistent performance across diverse scenarios using data from a single source. While latent diffusion models…
QianfanHuijin Technical Report: A Novel Multi-Stage Training Paradigm for Finance Industrial LLMs
Shupeng Li, Weipeng Lu, Linyun Liu +16
Domain-specific enhancement of Large Language Models (LLMs) within the financial context has long been a focal point of industrial application. While previous models such as Bloomb…
Efficient Online Continual Learning in Sensor-Based Human Activity Recognition
Yao Zhang, Souza Leite Clayton, Yu Xiao
Machine learning models for sensor-based human activity recognition (HAR) are expected to adapt post-deployment to recognize new activities and different ways of performing existin…
SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval
Yuqi Xiao, Yingying Zhu
Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations. Existing CLI…