17 papers
UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment
Zijian Gu, Weikai Lin, Shuang Zhou +2
Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploi…
The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory
Zihan Chen, Songwei Dong, Chengshuai Shi +4
Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update without checking whether it impro…
Channel-Wise Mixed-Precision Quantization for Large Language Models
Zihan Chen, Bike Xie, Jundong Li +1
Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substan…
Generalist Graph Anomaly Detection via Prototype-Based Distillation
Yiming Xu, Zihan Chen, Zhen Peng +4
Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs,…
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory
Songwei Dong, Zihan Chen, Chengshuai Shi +3
Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluation…
A Survey of Scaling in Large Language Model Reasoning
Zihan Chen, Song Wang, Zhen Tan +6
The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. How…