3 papers
cs.LG2026
Context-weighted Discrete Flow Matching
Daniil Cherniavskii, Daniel Severo, Karen Ullrich
Discrete flow matching provides a flexible framework for generative modeling on discrete structures. However, the standard factorized training objective exposes the model to target…
cs.LG2025
Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search
Daniel Severo, Giuseppe Ottaviano, Matthew Muckley +2
Approximate nearest neighbor search for vectors relies on indexes that are most often accessed from RAM. Therefore, storage is the factor limiting the size of the database that can…
cs.LG2024
Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
Daniel Severo, Ashish Khisti, Alireza Makhzani
We present an optimal method for encoding cluster assignments of arbitrary data sets. Our method, Random Cycle Coding (RCC), encodes data sequentially and sends assignment informat…