Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
NeurIPSSpotlight2025
TL;DR
Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-level rewards that stru…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
reinforcement learning fine-tuning 3d
← All NeurIPS 2025 Spotlight papers · Browse the whole archive