activity
20242026
collaborators

8 papers

cs.LG2026

Symplectic Neural Networks for Learning Non-Separable Hamiltonians

Harsh Choudhary, Vyacheslav Kungurtsev, Chandan Gupta +2

Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample efficiency. Identifying the…

cs.CV2026

Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space

Yue Cao, Jianyang Gu, Vyacheslav Kungurtsev +4

Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset more effective than another rem…

cs.CV2025

CONCORD: Concept-Informed Diffusion for Dataset Distillation

Jianyang Gu, Haonan Wang, Ruoxi Jia +4

Dataset distillation (DD) has witnessed significant progress in creating small datasets that encapsulate rich information from large original ones. Particularly, methods based on g…

math.OC2025

Truss topology design under harmonic loads: Peak power minimization with semidefinite programming

Shenyuan Ma, Jakub Marecek, Vyacheslav Kungurtsev +1

Designing lightweight yet stiff structures that can withstand vibrations is a crucial task in structural optimization. Here, we present a novel framework for truss topology optimiz…

cs.LG2025

Group Distributionally Robust Dataset Distillation with Risk Minimization

Saeed Vahidian, Mingyu Wang, Jianyang Gu +3

Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the…

cs.LG2024

Dataset Distillation from First Principles: Integrating Core Information Extraction and Purposeful Learning

Vyacheslav Kungurtsev, Yuanfang Peng, Jianyang Gu +4

Dataset distillation (DD) is an increasingly important technique that focuses on constructing a synthetic dataset capable of capturing the core information in training data to achi…