Xue Yang

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

Yifan Zhou, Qihao Yang, Yan Li, et al.

DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models

Lifan Zheng, Xue Yang, Jiawei Chen, et al.

Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings

Sebastian Cajas Ordóñez, Felipe Ocampo Osorio, Dax Enshan Koh, et al.

MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

Yan Li, Zezi Zeng, Yifan Yang, et al.

Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection

Ruilin Li, Heming Zou, Xiufeng Yan, et al.

This paper addresses a problem in continual learning (where AI models learn new tasks sequentially without forgetting old ones) by improving how randomly initialized projection layers work with pre-trained models. The authors propose SCL-MGSM, a method that intelligently selects which random features to use rather than using purely random ones, making the system more stable and accurate when learning new tasks with limited examples.