PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization

no code implementations • 25 Feb 2024 • Xiangdi Meng, Damai Dai, Weiyao Luo, Zhe Yang, Shaoxiang Wu, Xiaochen Wang, Peiyi Wang, Qingxiu Dong, Liang Chen, Zhifang Sui

Although LoRA fine-tuning is effective, there is still a performance gap compared to full fine-tuning, since its weight update is limited to low-rank matrices.

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain

1 code implementation • 21 Feb 2024 • Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang

To address this, we introduce Embodied-Instruction-Evolution (EIE), an automatic framework for synthesizing instruction tuning examples in multimodal embodied environments.

Autonomous Driving Decision Making