28 citations · 68 across the 11 of their papers we have counts for
11 papers
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
Nurislam Tursynbek, Zhiqiang Lao, Heather Yu +2
Recent text-to-video diffusion transformers generate visually compelling frames, yet still struggle with temporal coherence, often producing flickering, drifting, or unstable motio…
Guiding Registration with Emergent Similarity from Pre-Trained Diffusion Models
Nurislam Tursynbek, Hastings Greer, Basar Demir +1
Diffusion models, while trained for image generation, have emerged as powerful foundational feature extractors for downstream tasks. We find that off-the-shelf diffusion models, tr…
Unsupervised Discovery of 3D Hierarchical Structure with Generative Diffusion Features
Nurislam Tursynbek, Marc Niethammer
Inspired by recent findings that generative diffusion models learn semantically meaningful representations, we use them to discover the intrinsic hierarchical structure in biomedic…
Smoothed Embeddings for Certified Few-Shot Learning
Mikhail Pautov, Olesya Kuznetsova, Nurislam Tursynbek +2
Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input o…
CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks
Mikhail Pautov, Nurislam Tursynbek, Marina Munkhoeva +3
In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks -- small modifications of the input that change the predictions. Beside…
Robustness Threats of Differential Privacy
Nurislam Tursynbek, Aleksandr Petiushko, Ivan Oseledets
Differential privacy (DP) is a gold-standard concept of measuring and guaranteeing privacy in data analysis. It is well-known that the cost of adding DP to deep learning model is i…
Adversarial Turing Patterns from Cellular Automata
Nurislam Tursynbek, Ilya Vilkoviskiy, Maria Sindeeva +1
State-of-the-art deep classifiers are intriguingly vulnerable to universal adversarial perturbations: single disturbances of small magnitude that lead to misclassification of most…
Black-Box Face Recovery from Identity Features
Anton Razzhigaev, Klim Kireev, Edgar Kaziakhmedov +2
In this work, we present a novel algorithm based on an it-erative sampling of random Gaussian blobs for black-box face recovery, given only an output feature vector of deep face re…
Follow the bisector: a simple method for multi-objective optimization
Alexandr Katrutsa, Daniil Merkulov, Nurislam Tursynbek +1
This study presents a novel Equiangular Direction Method (EDM) to solve a multi-objective optimization problem. We consider optimization problems, where multiple differentiable los…
Geometry-Inspired Top-k Adversarial Perturbations
Nurislam Tursynbek, Aleksandr Petiushko, Ivan Oseledets
The brittleness of deep image classifiers to small adversarial input perturbations has been extensively studied in the last several years. However, the main objective of existing p…
Data Driven Chiller Plant Energy Optimization with Domain Knowledge
Hoang Dung Vu, Kok Soon Chai, Bryan Keating +5
Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of over-simplif…