14 papers
Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection
Tadeusz Dziarmaga, Witold Sikora, Łukasz Struski +2
Top-k selection is a fundamental computational primitive with applications spanning databases, information retrieval, signal processing, and modern machine learning workloads, incl…
Fast LapSum: Exact Differentiable Top-k at Million Scale
Łukasz Struski, Joanna Wojciechowicz, Jakub Antczak +3
The top- operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning. Yet standard…
TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians
Marek Lisowski, Åukasz SmoliÅski, Kornel Howil +3
While Implicit Neural Representations (INRs) and dynamic 3D Gaussian Splatting (3DGS) achieve impressive results in video processing, they often fall short of producing representat…
SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
Jakub StÄpieÅ, Marcin Mazur, Jacek Tabor +1
Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Visio…
MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging
Kacper Marzol, Ignacy Kolton, Weronika Smolak-Dyżewska +6
Endoluminal endoscopic procedures are essential for diagnosing colorectal cancer and other severe conditions in the digestive tract, urogenital system, and airways. 3D reconstructi…
MeshSplats: Mesh-Based Rendering with Gaussian Splatting Initialization
RafaÅ Tobiasz, Grzegorz WilczyÅski, Marcin Mazur +3
Gaussian Splatting (GS) is a recent and pivotal technique in 3D computer graphics. GS-based algorithms almost always bypass classical methods such as ray tracing, which offer numer…