爱可可-爱生活
24-01-30 18:42 微博认证:AI博主 2025微博新锐新知博主

几篇论文实现代码:
《Adaptive Self-training Framework for Fine-grained Scene Graph Generation》(ICLR 2024) GitHub: github.com/rlqja1107/torch-ST-SGG [fig3]
《Sentence-level Prompts Benefit Composed Image Retrieval》(ICLR 2024) GitHub: github.com/chunmeifeng/SPRC
《SliceGPT: Compress Large Language Models by Deleting Rows and Columns》(2024) GitHub: github.com/microsoft/TransformerCompression
《GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians》(2023) GitHub: github.com/CuriousPercibal/GaussianAvatars [fig1]
《VerilogEval: Evaluating Large Language Models for Verilog Code Generation》(2023) GitHub: github.com/NVlabs/verilog-eval
《S4C: Self-Supervised Semantic Scene Completion with Neural Fields》(2023) GitHub: github.com/ahayler/s4c [fig2]
《Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning》(2023) GitHub: github.com/LostXine/crossway_diffusion [fig4]
《ZeroFlow: Scalable Scene Flow via Distillation》(2023) GitHub: github.com/kylevedder/zeroflow
《ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training》(2023) GitHub: github.com/ToniChopp/ECAMP [fig5]

发布于 北京