几篇论文实现代码：
《Revisiting the Integration of Convolution and Attention for Vision Backbone》(NeurIPS 2024) GitHub: github.com/rayleizhu/GLMix [fig4]
《Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective》(NeurIPS 2024) GitHub: github.com/ForestsKing/GLAFF [fig5]
《Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models》(NeurIPS 2024) GitHub: github.com/Eaphan/OLIVINE [fig7]
《EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector》(2024) GitHub: github.com/Choddeok/EmoSpherepp
《The GigaMIDI dataset with loops and expressive music performance detection》(2024) GitHub: github.com/Metacreation-Lab/GigaMIDI-Dataset
《InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders》(2024) GitHub: github.com/ElanaPearl/InterPLM
《Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions》(2024) GitHub: github.com/AIDC-AI/Marco-o1 [fig1]
《Hymba: A Hybrid-head Architecture for Small Language Models》(2024) GitHub: github.com/NVlabs/hymba
《SparseEnd2End: Obstacle 3D Detection and Tracking Architecture Based VisionTransformer》(2024) GitHub: github.com/ThomasVonWu/SparseEnd2End [fig2]
《PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling》(2024) GitHub: github.com/Zefan-Cai/KVCache-Factory [fig3]
《DAPE: Data-Adaptive Positional Encoding for Length Extrapolation》(2024) GitHub: github.com/chuanyang-Zheng/DAPE
《I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy》(2024) GitHub: github.com/mobs-fbk/llm_interaction_simulator
《MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images》(2024) GitHub: github.com/batmanlab/MedSyn [fig6]
《A Configurable Library for Generating and Manipulating Maze Datasets》(2024) GitHub: github.com/understanding-search/maze-dataset
《GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models》(2024) GitHub: github.com/leitro/GRIF-DM [fig8]
《Revisiting the Integration of Convolution and Attention for Vision Backbone》(NeurIPS 2024) GitHub: github.com/rayleizhu/GLMix [fig4]
《Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective》(NeurIPS 2024) GitHub: github.com/ForestsKing/GLAFF [fig5]
《Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models》(NeurIPS 2024) GitHub: github.com/Eaphan/OLIVINE [fig7]
《EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector》(2024) GitHub: github.com/Choddeok/EmoSpherepp
《The GigaMIDI dataset with loops and expressive music performance detection》(2024) GitHub: github.com/Metacreation-Lab/GigaMIDI-Dataset
《InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders》(2024) GitHub: github.com/ElanaPearl/InterPLM
《Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions》(2024) GitHub: github.com/AIDC-AI/Marco-o1 [fig1]
《Hymba: A Hybrid-head Architecture for Small Language Models》(2024) GitHub: github.com/NVlabs/hymba
《SparseEnd2End: Obstacle 3D Detection and Tracking Architecture Based VisionTransformer》(2024) GitHub: github.com/ThomasVonWu/SparseEnd2End [fig2]
《PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling》(2024) GitHub: github.com/Zefan-Cai/KVCache-Factory [fig3]
《DAPE: Data-Adaptive Positional Encoding for Length Extrapolation》(2024) GitHub: github.com/chuanyang-Zheng/DAPE
《I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy》(2024) GitHub: github.com/mobs-fbk/llm_interaction_simulator
《MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images》(2024) GitHub: github.com/batmanlab/MedSyn [fig6]
《A Configurable Library for Generating and Manipulating Maze Datasets》(2024) GitHub: github.com/understanding-search/maze-dataset
《GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models》(2024) GitHub: github.com/leitro/GRIF-DM [fig8]
