AIConfPaper
← Search

Alexander Filippov

6 accepted papers

2026

CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models

Vladislav Pyatov, Gleb Bobrovskikh, Saveliy Galochkin, Nikita Boldyrev, Oleg Voynov, Alexander Filippov +3
CVPR 2026

We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories. Existing generative CAD systems are restricted to sketch-extrude operations due to simplified representations and limited datasets. We address this by introducing a Featur

Cited by 3Source ↗code ↗Scholar ↗
2026

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Daniil Selikhanovych, David Li, Aleksei Leonov, Nikita Gushchin, Sergei Kushneriuk, Alexander Filippov +3
ICML 2026poster

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate diffusion-based SR models, some (e.g., SinSR) fail to produce realistic perceptual details, while others (e.g., OSEDiff) …

Cited by 0Source ↗Scholar ↗
2025

A3D: Does Diffusion Dream about 3D Alignment?

Savva Victorovich Ignatyev, Nina Konovalova, Daniil Selikhanovych, Oleg Voynov, Nikolay Patakin, Ilya Olkov +6
ICLR 2025poster

We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods based on Score Distillation have succeeded in distilling the kno…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Quantization-Friendly Winograd Transformations for Convolutional Neural Networks

Vladimir Protsenko*, Vladimir Kryzhanovskiy, Alexander Filippov
ECCV 2024poster

"Efficient deployment of modern deep convolutional neural networks on resource-constrained devices suffers from demanding computational requirements of convolution operations. Quantization and use of Winograd convolutions operating on sufficiently large-tile inputs are two powerful strategies to spe…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2021

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

Alexander Korotin, Lingxiao Li, Aude Genevay, Justin Solomon, Alexander Filippov, Evgeny Burnaev
NeurIPS 2021poster

Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance. In this paper, we address this issue for quadratic-cost transport---specifically, computation of the Wasserstein-2 distance, a commonly-used…

Cited by 81Source ↗PDF ↗Scholar ↗
2021

Manifold Topology Divergence: a Framework for Comparing Data Manifolds.

Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, Alexander Filippov +1
NeurIPS 2021poster

We propose a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. We describe a novel tool, Cross-Barcode(P,Q), that, given a pair of distributions in a high-dimensional space, tracks multiscale topology spacial discrepancies between manifol…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗