2024-04-17 20:40
本条微博链接
几篇论文实现代码:《Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions》(ICLR 2024) GitHub: github.com/joonkeekim/Instructive-Decoding [fig6]《Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization》(ICLR 2024) GitHub: github.com/Lei-Kun/uni-o4《Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking》(CVPR 2024) GitHub: github.com/VVeiCao/Motion2VecSets [fig3]《Map-Relative Pose Regression for
………………………………