10 papers
DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
Yulong Li, Rong Xia, Yuxuan Zhang +12
We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from hum…
Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?
Xiwei Liu, Yulong Li, Xinlin Zhuang +5
Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood. It is underexplored whethe…
TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report Generation
Zhixiang Lu, Xiwei Liu, Sifan Song +5
Transcatheter Aortic Valve Replacement (TAVR) planning requires meticulous multimodal reasoning. However, adapting Multimodal Large Language Models (MLLMs) to this high-stakes doma…
DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality Learning
Xiwei Liu, Yulong Li, Feilong Tang +1
Adapting Large Multimodal Models (LMMs) to real-world scenarios poses the dual challenges of learning from sequential data streams while handling frequent modality incompleteness,…
ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models
Xiwei Liu, Yulong Li, Xinlin Zhuang +5
Medical Vision-Language Models have shown promising potential in clinical decision support, yet they remain prone to factual hallucinations due to insufficient grounding in localiz…
DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
Yulong Li, Jianxu Chen, Xiwei Liu +9
Medical foundation models generate narrative explanations but cannot quantify intervention effects, detect evidence conflicts, or validate literature claims, limiting clinical audi…
Path-Guided Flow Matching for Dataset Distillation
Xuhui Li, Zhengquan Luo, Xiwei Liu +2
Dataset distillation compresses large datasets into compact synthetic sets with comparable performance in training models. Despite recent progress on diffusion-based distillation,…
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 Robust Visual Continual Learning with Multi-Prototype Supervision
Xiwei Liu, Yulong Li, Yichen Li +4
Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL).…
SSS: Semi-Supervised SAM-2 with Efficient Prompting for Medical Imaging Segmentation
Hongjie Zhu, Xiwei Liu, Rundong Xue +5
In the era of information explosion, efficiently leveraging large-scale unlabeled data while minimizing the reliance on high-quality pixel-level annotations remains a critical chal…