A generalist vision encoder must capture semantic, spatial, language-aligned, and action-relevant cues within a unified representation, yet softmax attention underlying today's most capable visual backbones becomes prohibitively expensive at high resolution. A natural attempt to address both challenges is to distill mu...
Jia-Xie Huang, Yue Hu, Xin-Liang-Ma-Ming-Fu Zhu et al.· 0 citations
Flow matching is central to 3D generation, yet in practice its reinforcement learning (RL) methods are largely adapted from 2D visual generation. Representative DPO-, GRPO-, and NFT-style objectives, when applied to negative trajectories, mainly steer predicted velocities away from the corresponding directions without...
Zhen-Wu-Yong Zhou, Zhi-Wei Ning, Pu-Hua Jiang et al.· 0 citations
This work proposes Flow3D-OPD, a two-stage post-training framework that introduces multi-teacher distillation into 3D geometry generation and achieves consistent improvements across all geometric quality dimensions and surpasses all teacher models in the average metric.
Zhi-Wei Ning, Zhen-Wu-Yong Zhou, Pu-Hua Jiang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
