6 papers
Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields
Amir Mallak, Alaa Maalouf, Lior Wolf +2
Neural fields (NFs) map continuous coordinates to signals such as color or density, but fast high-quality reconstruction from sparse observations remains difficult. Classical Neura…
Predicting 3D structure by latent posterior sampling
Azmi Haider, Dan Rosenbaum
The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of bot…
BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation
Richard Hildebrandt, Evangelos Kourlitis, Baran Hashemi +7
We introduce a new strategy for compositional neural surrogates for radiation-matter interactions, a key task spanning domains from particle physics through nuclear and space engin…
Looking Into the Water by Unsupervised Learning of the Surface Shape
Ori Lifschitz, Tali Treibitz, Dan Rosenbaum
We address the problem of looking into the water from the air, where we seek to remove image distortions caused by refractions at the water surface. Our approach is based on modeli…
Flow Matching Neural Processes
Hussen Abu Hamad, Dan Rosenbaum
Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling and conditional sampling. We introduce a new…
Robust Neural Processes for Noisy Data
Chen Shapira, Dan Rosenbaum
Models that adapt their predictions based on some given contexts, also known as in-context learning, have become ubiquitous in recent years. We propose to study the behavior of suc…