几篇论文实现代码：
《VIGC: Visual Instruction Generation and Correction》(AAAI 2024) GitHub: github.com/opendatalab/VIGC [fig2]
《EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder》(AAAI 2024) GitHub: github.com/XiaoshuiHuang/EPCL [fig5]
《SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning》(ICML 2024) GitHub: github.com/LeapLabTHU/SimPro [fig6]
《Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models》(ACL 2024) GitHub: github.com/findalexli/mllm-dpo
《World-Grounded Human Motion Recovery via Gravity-View Coordinates》(SIGGRAPH Asia 2024) GitHub: github.com/zju3dv/GVHMR
《Automatically Labeling $200B Life-Saving Datasets: A Large Clinical Trial Outcome Benchmark》(2024) GitHub: github.com/chufangao/CTOD [fig1]
《DreamVoice: Text-Guided Voice Conversion》(2024) GitHub: github.com/myshell-ai/DreamVoice
《Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding》(2024) GitHub: github.com/YunzeMan/Lexicon3D [fig3]
《RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation》(2024) GitHub: github.com/HeegerGao/RiEMann
《AnyGraph: Graph Foundation Model in the Wild》(2024) GitHub: github.com/HKUDS/AnyGraph [fig4]
《Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts》(2024) GitHub: github.com/YeonwooSung/LIMoE-pytorch
《LaSagnA: Language-based Segmentation Assistant for Complex Queries》(2024) GitHub: github.com/congvvc/LaSagnA [fig7]
《𝙼𝚒𝚗𝚒𝙼𝚘𝚕: A Parameter-Efficient Foundation Model for Molecular Learning》(2024) GitHub: github.com/graphcore-research/minimol [fig8]
《UV-free Mesh Texture Generation with Denoising and Heat Diffusion》(2024) GitHub: github.com/simofoti/UV3-TeD
《View Selection for 3D Captioning via Diffusion Ranking》(2024) GitHub: github.com/tiangeluo/DiffuRank
《Critique-out-Loud Reward Models》(2024) GitHub: github.com/zankner/CLoud
《VIGC: Visual Instruction Generation and Correction》(AAAI 2024) GitHub: github.com/opendatalab/VIGC [fig2]
《EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder》(AAAI 2024) GitHub: github.com/XiaoshuiHuang/EPCL [fig5]
《SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning》(ICML 2024) GitHub: github.com/LeapLabTHU/SimPro [fig6]
《Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models》(ACL 2024) GitHub: github.com/findalexli/mllm-dpo
《World-Grounded Human Motion Recovery via Gravity-View Coordinates》(SIGGRAPH Asia 2024) GitHub: github.com/zju3dv/GVHMR
《Automatically Labeling $200B Life-Saving Datasets: A Large Clinical Trial Outcome Benchmark》(2024) GitHub: github.com/chufangao/CTOD [fig1]
《DreamVoice: Text-Guided Voice Conversion》(2024) GitHub: github.com/myshell-ai/DreamVoice
《Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding》(2024) GitHub: github.com/YunzeMan/Lexicon3D [fig3]
《RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation》(2024) GitHub: github.com/HeegerGao/RiEMann
《AnyGraph: Graph Foundation Model in the Wild》(2024) GitHub: github.com/HKUDS/AnyGraph [fig4]
《Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts》(2024) GitHub: github.com/YeonwooSung/LIMoE-pytorch
《LaSagnA: Language-based Segmentation Assistant for Complex Queries》(2024) GitHub: github.com/congvvc/LaSagnA [fig7]
《𝙼𝚒𝚗𝚒𝙼𝚘𝚕: A Parameter-Efficient Foundation Model for Molecular Learning》(2024) GitHub: github.com/graphcore-research/minimol [fig8]
《UV-free Mesh Texture Generation with Denoising and Heat Diffusion》(2024) GitHub: github.com/simofoti/UV3-TeD
《View Selection for 3D Captioning via Diffusion Ranking》(2024) GitHub: github.com/tiangeluo/DiffuRank
《Critique-out-Loud Reward Models》(2024) GitHub: github.com/zankner/CLoud
