13 papers
STEC-Net: A Spatiotemporal Graph Neural Framework for Community Discovery in Dynamic Social Networks
Yingnan Xu, Shuangshuang Chu
Community discovery is a central problem in the analysis of dynamic social networks. Traditional community discovery methods mainly focus on the formation and dissolution of links…
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
Zeyu Huang, Tianhao Cheng, Zihan Qiu +4
Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (…
OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation
Zhuoxiao Chen, Hongyang Yu, Ying Xu +3
Radiology report generation (RRG) aims to automatically produce clinically faithful reports from chest X-ray images. Prevailing work typically follows a scale-driven paradigm, by m…
Latent Adversarial Regularization for Offline Preference Optimization
Enyi Jiang, Yibo Jacky Zhang, Yinglun Xu +3
Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for lan…
Dynamic Topology Awareness: Breaking the Granularity Rigidity in Vision-Language Navigation
Jiankun Peng, Jianyuan Guo, Ying Xu +5
Vision-Language Navigation in Continuous Environments (VLN-CE) presents a core challenge: grounding high-level linguistic instructions into precise, safe, and long-horizon spatial…
TransMode-LLM: Feature-Informed Natural Language Modeling with Domain-Enhanced Prompting for Travel Behavior Modeling
Meijing Zhang, Ying Xu
Understanding traveler behavior and accurately predicting travel mode choice are at the heart of transportation planning and policy-making. This study proposes TransMode-LLM, an in…