几篇论文实现代码：
《DiffCLIP: Few-shot Language-driven Multimodal Classifier》(AAAI 2025) GitHub: github.com/icey-zhang/DiffCLIP [fig7]
《2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining》(2025) GitHub: github.com/DAMO-NLP-SG/multimodal_textbook [fig1]
《MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization》(2025) GitHub: github.com/tencent-ailab/MuQ
《Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data》(NeurIPS 2024) GitHub: github.com/LeapLabTHU/OVM3D-Det [fig3]
《ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention》(NeurIPS 2024) GitHub: github.com/ai4protein/ProSST [fig5]
《Prompt optimization in multi-step tasks (promst): Integrating human feedback and preference alignment》(EMNLP 2024) GitHub: github.com/yongchao98/PROMST
《ReNeg: Learning Negative Embedding with Reward Guidance》(2024) GitHub: github.com/LemonTwoL/ReNeg [fig2]
《Real-Time Whole-Body Control of Legged Robots with Model-Predictive Path Integral Control》(2024) GitHub: github.com/jrapudg/RTWholeBodyMPPI
《RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer》(2024) GitHub: github.com/seongho608/RingFormer [fig4]
《nuanced LLM jailbreaks》(2024) GitHub: github.com/facebookresearch/jailbreak-objectives [fig6]
《Stretching Each Dollar: Diffusion Training from Scratch on
a Micro-Budget》(2024) GitHub: github.com/SwayStar123/microdiffusion
《DiffCLIP: Few-shot Language-driven Multimodal Classifier》(AAAI 2025) GitHub: github.com/icey-zhang/DiffCLIP [fig7]
《2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining》(2025) GitHub: github.com/DAMO-NLP-SG/multimodal_textbook [fig1]
《MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization》(2025) GitHub: github.com/tencent-ailab/MuQ
《Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data》(NeurIPS 2024) GitHub: github.com/LeapLabTHU/OVM3D-Det [fig3]
《ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention》(NeurIPS 2024) GitHub: github.com/ai4protein/ProSST [fig5]
《Prompt optimization in multi-step tasks (promst): Integrating human feedback and preference alignment》(EMNLP 2024) GitHub: github.com/yongchao98/PROMST
《ReNeg: Learning Negative Embedding with Reward Guidance》(2024) GitHub: github.com/LemonTwoL/ReNeg [fig2]
《Real-Time Whole-Body Control of Legged Robots with Model-Predictive Path Integral Control》(2024) GitHub: github.com/jrapudg/RTWholeBodyMPPI
《RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer》(2024) GitHub: github.com/seongho608/RingFormer [fig4]
《nuanced LLM jailbreaks》(2024) GitHub: github.com/facebookresearch/jailbreak-objectives [fig6]
《Stretching Each Dollar: Diffusion Training from Scratch on
a Micro-Budget》(2024) GitHub: github.com/SwayStar123/microdiffusion
