3 papers
cs.CV2026
HIFICL: High-Fidelity In-Context Learning for Multimodal Tasks
Xiaoyu Li, Yuhang Liu, Xuanshuo Kang +4
In-Context Learning (ICL) is a significant paradigm for Large Multimodal Models (LMMs), using a few in-context demonstrations (ICDs) for new task adaptation. However, its performan…
cs.CV2025
MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
Yuhang Liu, Wenjie Zhao, Xin Wang +1
Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address th…
cs.CV2025
H2ST: Hierarchical Two-Sample Tests for Continual Out-of-Distribution Detection
Yuhang Liu, Wenjie Zhao, Yunhui Guo
Task Incremental Learning (TIL) is a specialized form of Continual Learning (CL) in which a model incrementally learns from non-stationary data streams. Existing TIL methodologies…