1 citations · 1 across the 4 of their papers we have counts for
7 papers
Does Unlearning Survive Collaboration? Robust Unlearning for Shared-Model LLM Teams
Hengsong Liu, Liangyu Teng, Jingnan Cai +5
LLM unlearning is essential for removing sensitive or unwanted knowledge while preserving useful capabilities. As LLM teams are increasingly used to solve complex problems, forgett…
DISCERN: Identifiable Disease Evidence for Generalizable Medical Multimodal Learning
Xiaoguang Zhu, Pengyi Jiang, Juncen Guo +3
Clinical multimodal models can learn enrollment shortcuts shared across modalities and fail on new cohorts. We model these data through a latent structural causal model: disease st…
Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection
Liangyu Teng, Hengsong Liu, Juncen Guo +4
The performance ceiling of an LLM team is constrained not only by individual model capabilities, but also by inter-member error resonance and predictive differences. Although heter…
Embracing Aleatoric Uncertainty in Medical Multimodal Learning with Missing Modalities
Linxiao Gong, Yang Liu, Lianlong Sun +3
Medical multimodal learning faces significant challenges with missing modalities prevalent in clinical practice. Existing approaches assume equal contribution of modality and rando…
Robust Multimodal Representation Learning in Healthcare
Xiaoguang Zhu, Linxiao Gong, Lianlong Sun +3
Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world med…
Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities
Xiaoguang Zhu, Lianlong Sun, Yang Liu +4
Medical multimodal representation learning aims to integrate heterogeneous clinical data into unified patient representations to support predictive modeling, which remains an essen…
Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning
Juncen Guo, Xiaoguang Zhu, Liangyu Teng +4
Class-incremental Learning (CIL) enables the model to incrementally absorb knowledge from new classes and build a generic classifier across all previously encountered classes. When…