Human Pose as Compositional Tokens
人体姿态作为构图令牌.
Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation
广义人体姿态估计中的自校正与自适应推理.
Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
用于参数高效微调的自适应预算分配.
DeepMIM: Deep Supervision for Masked Image Modeling
DeepMIM：掩码图像建模中的深度监督.
Masked Image Modeling with Local Multi-Scale Reconstruction
通过局部多尺度重构进行掩码图像建模.
Symbolic Discovery of Optimization Algorithms
优化算法的符号发现.