4 papers
APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation
Dongliang Chen, Xinlin Zhuang, Junjie Xu +8
Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to…
CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection
Xinlin Zhuang, Yichen Li, Xiwei Liu +11
Adapting CLIP to vertical domains is typically approached by novel fine-tuning strategies or by continual pre-training (CPT) on large domain-specific datasets. Yet, data itself rem…
Towards Efficient Medical Reasoning with Minimal Fine-Tuning Data
Xinlin Zhuang, Feilong Tang, Haolin Yang +9
Supervised Fine-Tuning (SFT) of the language backbone plays a pivotal role in adapting Vision-Language Models (VLMs) to specialized domains such as medical reasoning. However, exis…
Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models
Xinlin Zhuang, Jiahui Peng, Ren Ma +7
The composition of pre-training datasets for large language models (LLMs) remains largely undisclosed, hindering transparency and efforts to optimize data quality, a critical drive…