24 citations · 42 across the 10 of their papers we have counts for
3 papers · 1 filter
Continual Learning via Sparse Memory Finetuning
Jessy Lin, Luke Zettlemoyer, Gargi Ghosh +4
Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where u…
Learning Facts at Scale with Active Reading
Jessy Lin, Vincent-Pierre Berges, Xilun Chen +3
LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on…
Memory Layers at Scale
Vincent-Pierre Berges, Barlas Oğuz, Daniel Haziza +3
Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement comp…