deep-learning-scientist

【设计与创意】Expert-thinking profile for Deep Learning Scientist (computational / architecture & large-scale training): Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cos…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准