Sparse Autoencoders (SAEs) began as an unsupervised tool for decomposing neural representations into sparse, interpretable features, and are increasingly used not only for passive analysis but also for active interventions such as unlearning, bias mitigation, and concept editing. A central challenge for these editing a...
Jakub Stepien, M. Mazur, J. Tabor et al.· 0 citations
Prof-K is introduced, a fast, scalable, and distribution-agnostic algorithm for exact top-k selection that derives high-probability guarantees for correctness and buffer size, together with an approximately optimal sample size that minimizes overhead as a function of N and k.
Tadeusz Dziarmaga, W. Sikora, L. Struski et al.· 2 citations
Selecting the top-$k$ elements is a fundamental operation for inducing sparsity in large-scale models and optimization problems, enabling robust expert activation, token routing or attention pruning. However, hard top-$k$ is non-differentiable, while existing differentiable alternatives become increasingly expensive as...
J. Antczak, Joanna Wojciechowicz, Kamil Książek et al.· 0 citations
TOM-GS is introduced, an editable video representation that forgoes complex deformations in favor of regular 3D Gaussians equipped with a continuous temporal opacity formulation, which enables static 3D spatial components to fade smoothly in and out of the scene.
Marek Lisowski, Łukasz Smoliński, Kornel Howil et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
