2 papers
cs.CV2026
Multimodal Fusion for Sim2real Transfer in Visual Reinforcement Learning
Zichun Xu, Jingdong Zhao, Chenyu Guo +6
Depth information is robust to scene appearance variations and inherently carries 3D spatial details. Thus, a visual backbone based on the vision transformer is proposed to fuse RG…
cs.CV2025
LoRA-Based Continual Learning with Constraints on Critical Parameter Changes
Shimou Ling, Liang Zhang, Jiangwei Zhao +2
LoRA-based continual learning represents a promising avenue for leveraging pre-trained models in downstream continual learning tasks. Recent studies have shown that orthogonal LoRA…