5 papers
M3DA: Benchmark for Unsupervised Domain Adaptation in 3D Medical Image Segmentation
Boris Shirokikh, Anvar Kurmukov, Mariia Donskova +3
Domain shift presents a significant challenge in applying Deep Learning to the segmentation of 3D medical images from sources like Magnetic Resonance Imaging (MRI) and Computed Tom…
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4
We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation…
FLAME: Flexible LLM-Assisted Moderation Engine
Ivan Bakulin, Ilia Kopanichuk, Iaroslav Bespalov +4
The rapid advancement of Large Language Models (LLMs) has introduced significant challenges in moderating user-model interactions. While LLMs demonstrate remarkable capabilities, t…
Tensor-Train Point Cloud Compression and Efficient Approximate Nearest-Neighbor Search
Georgii Novikov, Alexander Gneushev, Alexey Kadeishvili +1
Nearest-neighbor search in large vector databases is crucial for various machine learning applications. This paper introduces a novel method using tensor-train (TT) low-rank tensor…
Anatomical Positional Embeddings
Mikhail Goncharov, Valentin Samokhin, Eugenia Soboleva +5
We propose a self-supervised model producing 3D anatomical positional embeddings (APE) of individual medical image voxels. APE encodes voxels' anatomical closeness, i.e., voxels of…