3 papers
cs.LG2025
GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning
Jie Ou, Shuaihong Jiang, Yingjun Du +1
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, DoRA, and HiRA, enable lightweight adaptation of large pre-trained models via low-rank updates. However, existing PEFT…
cs.CV2024
QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain
Wenfang Sun, Yingjun Du, Gaowen Liu +2
We tackle the problem of quantifying the number of objects by a generative text-to-image model. Rather than retraining such a model for each new image domain of interest, which lea…
cs.AI2024
CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation
Jie Liu, Pan Zhou, Yingjun Du +4
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods ofte…