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.CV2026
Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems
Antonios Tragoudaras, Chenyu Zhang, Daniil Cherniavskii +7
Recent advances in image and video generation raise hopes that these models possess world modeling capabilities-the ability to generate realistic, physically plausible videos. This…
cs.LG2024
Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices
Elizaveta Kostenok, Daniil Cherniavskii, Alexey Zaytsev
Transformer-based language models have set new benchmarks across a wide range of NLP tasks, yet reliably estimating the uncertainty of their predictions remains a significant chall…