专栏名称: 爱可可-爱生活
知名互联网资讯博主 北邮PRIS模式识别实验室陈老师
目录
相关文章推荐
信息平权  ·  制裁?送钱罢了 ·  2 天前  
信息平权  ·  制裁?送钱罢了 ·  2 天前  
爱可可-爱生活  ·  【TemporalBench:视频理解基准测 ... ·  4 天前  
爱可可-爱生活  ·  [LG]《Discovering Data ... ·  1 周前  
51好读  ›  专栏  ›  爱可可-爱生活

几篇论文实现代码:《Multiview Scene Graph》-20241110180116

爱可可-爱生活  · 微博  · AI  · 2024-11-10 18:01

正文

2024-11-10 18:01

几篇论文实现代码:
《Multiview Scene Graph》(NeurIPS 2024) GitHub: github.com/ai4ce/MSG [fig3]
《BELM: High-quality Exact Inversion sampler of Diffusion Models》(NeurIPS 2024) GitHub: github.com/zituitui/BELM [fig4]
《Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices》(NeurIPS 2024) GitHub: github.com/AndPotap/einsum-search [fig6]
《Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification》(NeurIPS 2024) GitHub: github.com/LUOyk1999/tunedGNN
《OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models》(2024) GitHub: github.com/OpenCoder-llm/OpenCoder-llm [fig1]
《SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation》(2024) GitHub: github.com/Kmcode1/SG-I2V
《Model Merging with SVD to Tie the KnOTS》(2024) GitHub: github.com/gstoica27/KnOTS [fig2]
《Manifold Diffusion Geometry: Curvature, Tangent Spaces, and Dimension》(2024) GitHub: github.com/Iolo-Jones/ManifoldDiffusionGeometry
《LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation》(2024) GitHub: github.com/microsoft/LLM2CLIP
《VoiceBench: Benchmarking LLM-Based Voice Assistants》(2024) GitHub: github.com/MatthewCYM/VoiceBench
《LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch》(2024) GitHub: github.com/caigaojiang/LLMOPT [fig5]
《LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models》(2024) GitHub: github.com/Fsoft-AIC/LibMoE
《Differentiable simulation enables large-scale training of detailed biophysical models of neural dynamics》(2024) GitHub: github.com/jaxleyverse/jaxley
《BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training》(2024) GitHub: github.com/pchizhov/picky_bpe
《A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks》(2024) GitHub: github.com/ml-jku/LRAM [fig7]
《Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion》(2024) GitHub: github.com/oooolga/Ctrl-V [fig8]