activity
20162026
most citedDeep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

180 citations · 519 across the 23 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.CV2025

NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation

Yu Zeng, Charles Ochoa, Mingyuan Zhou +3

Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image genera…