Improving Multimodal Large Language Models Using Continual Learning — mentioned by chriskanan

Sat, 15 Mar 2025 14:31:47 GMT

Depends on what angle you are interested in. If you are interested in continual learning for something like mitigating model drift such that a model can stay up-to-date where the goal is attain speed ups during training see these works: Compared to other methods for continual learning on ImageNet-1K, SIESTA requires 7x-60x less compute than other methods and achieves the same performance as a model trained in an offline/batch manner. It also works for arbitrary distributions rather than a lot of continual learning methods that only work for specific distributions (and hence don't really match…

Paper and discussion history. A mention is not an endorsement.

Improving Multimodal Large Language Models Using Continual Learning · HackerPapers discussions

Improving Multimodal Large Language Models Using Continual Learning — mentioned by chriskanan