39 citations · 55 across the 9 of their papers we have counts for
9 papers
MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models
Yuncheng Yang, Feiyang Ye, Shixian Luo +7
Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving effici…
Task-Aware Low-Rank Adaptation of Segment Anything Model
Xuehao Wang, Feiyang Ye, Yu Zhang
The Segment Anything Model (SAM), with its remarkable zero-shot capability, has been proven to be a powerful foundation model for image segmentation tasks, which is an important ta…
A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization
Feiyang Ye, Baijiong Lin, Xiaofeng Cao +2
In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level su…
A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting
Jinjing Zhu, Feiyang Ye, Qiao Xiao +3
Despite the progress made in domain adaptation, solving Unsupervised Domain Adaptation (UDA) problems with a general method under complex conditions caused by label shifts between…
Dual-Balancing for Multi-Task Learning
Baijiong Lin, Weisen Jiang, Feiyang Ye +6
Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among t…
A Fast Attention Network for Joint Intent Detection and Slot Filling on Edge Devices
Liang Huang, Senjie Liang, Feiyang Ye +1
Intent detection and slot filling are two main tasks in natural language understanding and play an essential role in task-oriented dialogue systems. The joint learning of both task…
Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning
Baijiong Lin, Feiyang Ye, Yu Zhang +1
Multi-Task Learning (MTL) has achieved success in various fields. However, how to balance different tasks to achieve good performance is a key problem. To achieve the task balancin…
Deep Safe Multi-Task Learning
Zhixiong Yue, Feiyang Ye, Yu Zhang +2
In recent years, Multi-Task Learning (MTL) has attracted much attention due to its good performance in many applications. However, many existing MTL models cannot guarantee that th…
Multi-Objective Meta Learning
Feiyang Ye, Baijiong Lin, Zhixiong Yue +3
Meta learning with multiple objectives can be formulated as a Multi-Objective Bi-Level optimization Problem (MOBLP) where the upper-level subproblem is to solve several possible co…