几篇论文实现代码：
《SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing》(ACL 2022) GitHub: github.com/microsoft/SpeechT5 [fig3]
《Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction》(NAACL 2022) GitHub: github.com/zjunlp/HVPNeT [fig2]
《Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods》(NeurIPS 2021) GitHub: github.com/desi-ivanova/idad
《Generalizable Imitation Learning from Observation via Inferring Goal Proximity》(NeurIPS 2021) GitHub: github.com/clvrai/goal_prox_il [fig7]
《BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework》(2022) GitHub: github.com/ADLab-AutoDrive/BEVFusion [fig1]
《Prompt-aligned Gradient for Prompt Tuning》(2022) GitHub: github.com/BeierZhu/Prompt-align [fig6]
《Robust Training under Label Noise by Over-parameterization》(2022) GitHub: github.com/shengliu66/SOP
《Breaking the Chain of Gradient Leakage in Vision Transformers》(2022) GitHub: github.com/yhlleo/MJP [fig5]
《BERT Goes Shopping: Comparing Distributional Models for Product Representations》(2021) GitHub: github.com/vinid/prodb [fig4]