晓飞的算法工程笔记

论文: A Simple Image Segmentation Framework via In-Context Examples 论文地址：https://arxiv.org/abs/2410.04

论文: Improving Object Detection via Local-global Contrastive Learning 论文地址：https://arxiv.org/abs/2410

论文: Exploring the Benefit of Activation Sparsity in Pre-training 论文地址：https://arxiv.org/abs/2410.034

论文: Collective Critics for Creative Story Generation 论文地址：https://arxiv.org/abs/2410.02428 创新点 提出了 $

论文: Parameter Competition Balancing for Model Merging 论文地址：https://arxiv.org/abs/2410.02396 论文代码：htt

论文: Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models 论文地址：htt

论文: MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models 论文地址：https://arxiv.org/abs

论文: VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection 论文地址：https://arxiv.org/abs/24

论文: CNN Mixture-of-Depths 论文地址：https://arxiv.org/abs/2409.17016 创新点 提出新的卷积轻量化结构MoD，在卷积块（Conv-Blocks）