4 papers across 3 sessions
A lightweight approach that adaptively patches the input image to increase token information density and encode hierarchical spatial structures into the input embedding.
This paper introduces hyperbolic space into dataset distillation for the first time.
We present an efficient $O(n \ln T)$-regret method for online inverse linear optimization, extend it to suboptimal feedback, and provide an $\Omega(n)$-regret lower bound.