12 papers
EvoPrompt: Guided Prompt Evolution for Vision-Language Models Adaptation
Enming Zhang, Jiayang Li, Yanlong Wang +3
The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning…
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
Chengfeng Wu, Tao Zou, Yanru Wu +1
Multi-task learning (MTL) aims to construct a joint model for multiple tasks by sharing a common representation across domains. To achieve this goal, existing optimization-centric…
Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training
Yanru Wu, Jianning Wang, Chongxin Gan +1
Training general-purpose Audio Large Language Models (ALLMs) across diverse datasets is essential for holistic audio understanding, yet it faces significant challenges due to datas…
Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework
Qingyue Zhang, Chang Chu, Haohao Fu +5
In multi-source transfer learning, a key challenge lies in how to appropriately differentiate and utilize heterogeneous source tasks. However, existing multi-source methods typical…
Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
Yanru Wu, Jianning Wang, Xiangyu Chen +4
Continual learning (CL) has been a critical topic in contemporary deep neural network applications, where higher levels of both forward and backward transfer are desirable for an e…
A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
Qingyue Zhang, Haohao Fu, Guanbo Huang +7
Multi-source transfer learning provides an effective solution to data scarcity in real-world supervised learning scenarios by leveraging multiple source tasks. In this field, exist…