Christian LinSwin Transformer: Hierarchical Vision Transformer using Shifted WindowsThis study introduces a new tool for computer vision called the Swin Transformer. This tool is built on the Transformer model, which was…Oct 13, 20232Oct 13, 20232
Christian LinVision Transformer ~ Am Image is Worth 16X16 Words: Transformers for Image Recognition at ScaleIn the ever-evolving landscape of machine learning, the “Vision Transformer” (ViT) marks a significant departure from conventional wisdom…Oct 8, 2023Oct 8, 2023
Christian LinTransformer ~ Attention is All You NeedIn the groundbreaking paper “Attention is All You Need,” researchers from Google introduced the Transformer architecture, a novel approach…Oct 7, 2023Oct 7, 2023
Christian LinComputer Vision Paper ~ DiffPose: Toward More Reliable 3D Pose Estimation3D human pose estimation from a single image is a challenging task due to the inherent ambiguity and occlusion that can lead to high…Jun 22, 2023Jun 22, 2023
Christian LinComputer Vision Paper ~ PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human…In recent times, there have been successful methods using transformers to estimate human poses in 3D from 2D sequential data. One such…Jun 18, 2023Jun 18, 2023
Christian LinLarge Language Model Paper Reading~LoRA: Low-Rank Adaptation of Large Language ModelsA significant approach in natural language processing involves training large-scale models on general data and adapting them to specific…Jun 10, 2023Jun 10, 2023
Christian LinReinforcement Learning Paper Reading~Is Conditional Generative Modeling All You Need for…Recent advancements in conditional generative modeling have opened up possibilities for generating high-quality images solely based on…May 20, 20231May 20, 20231
Christian Lin一個『幸運』的旅途~Microsoft Research Development Intern2022–2023 微軟RDI實習生分享Apr 29, 2023Apr 29, 2023
Christian LinReinforcement Learning Paper Reading~Planning with Diffusion for Flexible Behavior SynthesisThe paper introduces a new approach to model-based reinforcement learning, in which as much of the trajectory optimization process as…Apr 23, 20231Apr 23, 20231