Europe
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g.
Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
Although the population (i.e, infinite-particle) limit dynamics of SVGD is well characterized, its behavior in the finite-particle regime is far less understood.
Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
Although the population (i.e, infinite-particle) limit dynamics of SVGD is well characterized, its behavior in the finite-particle regime is far less understood.
Revisiting Ensembling in One-Shot Federated Learning
The overall learning procedure is illustrated in Figure 1, alongside iterative and one-shot FL. 1.1 Our Contributions
Geometry-Aware Adaptation for Pretrained Models
Machine learning models--including prominent zero-shot models--are often trained on datasets whose labels are only a small proportion of a larger label space. Such spaces are commonly equipped with a metric that relates the labels via distances between them.
Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
We provide both theoretical analysis and experimental results to validate the effectiveness of our proposed algorithm.