Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models
Paper • 2605.14938 • Published • 1
Yuehao Liu
YuehaoLiu
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models authored a paper 1 day ago
ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing upvoted a paper 1 day ago
MMSkills: Towards Multimodal Skills for General Visual AgentsOrganizations
authored 2
papers 1 day ago