PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space Paper • 2607.05373 • Published 28 days ago • 66
view article Article Illustrating Reinforcement Learning from Human Feedback (RLHF) +2 natolambert, LouisCastricato, lvwerra, Dahoas • Dec 9, 2022 • 419
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories Paper • 2503.08625 • Published Mar 11, 2025 • 27