Search Results for author:
Found 2 papers, 1 papers with code
CoTBal: Comprehensive Task Balancing for Multi-Task Visual Instruction Tuning
To mitigate this issue, we propose a novel Comprehensive Task Balancing (CoTBal) algorithm for multi-task visual instruction tuning of LMMs.
Improvable Gap Balancing for Multi-Task Learning
In this paper, following the loss balancing framework, we propose two novel improvable gap balancing (IGB) algorithms for MTL: one takes a simple heuristic, and the other (for the first time) deploys deep reinforcement learning for MTL.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
