PERL augments frozen CLIP with a shared recurrent reasoning module of roughly 6K parameters that iteratively refines representations via latent token injection, delivering strong base-to-novel and transfer performance across 15 benchmarks.
Looped transformers as programmable computers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Minimal weight norm of fixed-precision looped neural networks equals Kolmogorov complexity of output string up to log factor, making weight decay match the optimal universal prior up to polynomial factor.
citing papers explorer
-
PERL: Parameter Efficient Reasoning in CLIP Latent Space
PERL augments frozen CLIP with a shared recurrent reasoning module of roughly 6K parameters that iteratively refines representations via latent token injection, delivering strong base-to-novel and transfer performance across 15 benchmarks.
-
Neural Weight Norm = Kolmogorov Complexity
Minimal weight norm of fixed-precision looped neural networks equals Kolmogorov complexity of output string up to log factor, making weight decay match the optimal universal prior up to polynomial factor.