几篇论文实现代码：
《Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.》(ICML 2024) GitHub: github.com/ys-zong/VLGuard
《Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition》(ICLR 2024) GitHub: github.com/NVlabs/CMD
《VkD : Improving Knowledge Distillation using Orthogonal Projections》(CVPR 2024) GitHub: github.com/roymiles/vkd
《Bilateral Propagation Network for Depth Completion》(CVPR 2024) GitHub: github.com/kakaxi314/BP-Net
《Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching》(CVPR 2024) GitHub: github.com/Windsrain/Selective-Stereo
《Pandora: Towards General World Model with Natural Language Actions and Video States》(2024) GitHub: github.com/maitrix-org/Pandora [fig1]
《Improved Distribution Matching Distillation for Fast Image Synthesis》(2024) GitHub: github.com/tianweiy/DMD2
《AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field》(2024) GitHub: github.com/RongLiu-Leo/AtomGS
《DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis》(2024) GitHub: github.com/tyshiwo1/DiM-DiffusionMamba
《VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding》(2024) GitHub: github.com/YueFan1014/VideoAgent [fig2]
《Visual Whole-Body Control for Legged Loco-Manipulation》(2024) GitHub: github.com/Ericonaldo/visual_wholebody
《EditWorld: Simulating World Dynamics for Instruction-Following Image Editing》(2024) GitHub: github.com/YangLing0818/EditWorld
《MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise》(2024) GitHub: github.com/lxirich/MM-Retinal
《Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model》(2024) GitHub: github.com/XiaoduoAILab/XmodelVLM [fig3]
《TerDiT: Ternary Diffusion Models with Transformers》(2024) GitHub: github.com/Lucky-Lance/TerDiT