Zobrazeno 1 - 10
of 380 149
pro vyhledávání: '"Tran, Than"'
Recent approaches have yielded promising results in distilling multi-step text-to-image diffusion models into one-step ones. The state-of-the-art efficient distillation technique, i.e., SwiftBrushv2 (SBv2), even surpasses the teacher model's performa
Externí odkaz:
http://arxiv.org/abs/2412.02687
Autor:
Tran, Nhan Tri, Tran, Lan Nguyen
Intermolecular charge-transfer (xCT) excited states important for various practical applications are challenging for many standard computational methods. It is highly desirable to have an affordable method that can treat xCT states accurately. In the
Externí odkaz:
http://arxiv.org/abs/2411.00251
Publikováno v:
38th Conference on Neural Information Processing Systems (NeurIPS 2024
This paper aims at developing novel shuffling gradient-based methods for tackling two classes of minimax problems: nonconvex-linear and nonconvex-strongly concave settings. The first algorithm addresses the nonconvex-linear minimax model and achieves
Externí odkaz:
http://arxiv.org/abs/2410.22297
Diffusion models have demonstrated remarkable capabilities in image synthesis, but their recently proven vulnerability to Membership Inference Attacks (MIAs) poses a critical privacy concern. This paper introduces two novel and efficient approaches (
Externí odkaz:
http://arxiv.org/abs/2410.16657
Motion planning is an essential process for the navigation of unmanned aerial vehicles (UAVs) where they need to adapt to obstacles and different structures of their operating environment to reach the goal. This paper presents an optimal motion plann
Externí odkaz:
http://arxiv.org/abs/2410.09799
Designing neural network architectures that can handle data symmetry is crucial. This is especially important for geometric graphs whose properties are equivariance under Euclidean transformations. Current equivariant graph neural networks (EGNNs), p
Externí odkaz:
http://arxiv.org/abs/2410.04692
Autor:
Vo, Thieu N., Tran, Viet-Hoang, Huu, Tho Tran, The, An Nguyen, Tran, Thanh, Nguyen-Nhat, Minh-Khoi, Pham, Duy-Tung, Nguyen, Tan Minh
Neural Functional Networks (NFNs) have gained increasing interest due to their wide range of applications, including extracting information from implicit representations of data, editing network weights, and evaluating policies. A key design principl
Externí odkaz:
http://arxiv.org/abs/2410.04213
Autor:
Tran, Viet-Hoang, Vo, Thieu N., The, An Nguyen, Huu, Tho Tran, Nguyen-Nhat, Minh-Khoi, Tran, Thanh, Pham, Duy-Tung, Nguyen, Tan Minh
This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or sparsity patterns of a deep neural network (DNN) as input data and have prove
Externí odkaz:
http://arxiv.org/abs/2410.04209
In this study, we address causal inference when only observational data and a valid causal ordering from the causal graph are available. We introduce a set of flow models that can recover component-wise, invertible transformation of exogenous variabl
Externí odkaz:
http://arxiv.org/abs/2412.09843
Autor:
Terhune, J. E. S., Elwell, R., Tan, H. B. Tran, Perera, U. C., Morgan, H. W. T., Alexandrova, A. N., Derevianko, Andrei, Hudson, Eric R.
The population dynamics of the 229Th isomeric state is studied in a solid-state host under laser illumination. A photoquenching process is observed, where off-resonant vacuum-ultraviolet (VUV) radiation leads to relaxation of the isomeric state. The
Externí odkaz:
http://arxiv.org/abs/2412.08998