Parameter-efficient continual learning on pre-trained Vision Transformers largely relies on a costly premise: preventing catastrophic forgetting requires either spawning a dedicated LoRA branch per session---causing adapter parameters to scale linearly with task horizon---or applying sparse Mixture-of-Experts gating sy...
Wen-Hsuan Liu, Amara Okonkwo, Tom Saliencro et al.· 0 citations
Exemplar-free continual learning on pre-trained Vision Transformers increasingly relies on Low-Rank Adaptation (LoRA), yet prevailing methods govern the low-rank update space through strict subspace isolation. By projecting each incoming task into the approximate null space of historical token activations, isolation-ba...
Tom Saliencro, Wen-Hsuan Liu, Rohan Desai et al.· 0 citations
Mixture-of-LoRA-experts methods raise the capacity of low-rank adaptation by routing each token to a few low-rank experts. Nearly all of them tie one input-side factor to one output-side factor per expert, and nearly all of them route by scoring the token: the router picks experts without seeing what any of them would...
Priya Nair, Lukas Brenner, Maya Lindqvist et al.· 0 citations
This work introduces CARE (Confidence-Adaptive Routing of Experts), which admits experts in a nucleus fashion and improves over fixed top-k MoE-LoRA at matched compute and matches the fixed-k=4 baseline while activating fewer experts.
Tom Saliencro, Rohan Desai, Priya Nair et al.· arXiv.org· 1 citation
Mixtures of low-rank adaptation experts increase parameter-efficient capacity by routing each input through a subset of adapters. Recent dynamic routers activate more experts when the router or prediction is uncertain. This rule silently equates uncertainty with useful additional computation: an uncertain example may c...
Tom Saliencro, Rohan Desai, Priya Nair et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.