2 papers
cs.LG2026
Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
Silen Naihin, Lev Stambler
Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm. Features that fire on token…
cs.LG2026
CLaaS: Continual learning as a service for sample efficient online learning
Kion Fallah, Silen Naihin, Barak Widawsky +1
Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain pr…