논문리뷰 – TildAlice

Transformer Review: Attention Is All You Need 완전 분석

2026년 01월 04일

Transformer self-attention math decoded: positional encoding, multi-head mechanics, and why it beat RNN/LSTM. Full equations + ablations.

2026년 01월 04일

Classifier-Free Guidance doubles diffusion model quality without extra networks. Guidance scale tuning math + Stable Diffusion internals.

2026년 01월 03일

DDPM diffusion models explained: forward/reverse process math, simplified loss function derivation, and U-Net architecture that changed AI.

2025년 12월 12일

Mamba hits O(L) complexity vs Transformer's O(L²). Selective State Space Model achieves 5× faster inference on DNA and audio with benchmarks.

2025년 12월 07일

FlashAttention cuts Transformer memory from O(N²) to O(N) while running 2-4× faster. Here's the IO-aware tiling trick explained.

2025년 12월 07일

RetNet achieves 8.4× faster inference than Transformer with 70% less memory. The parallel training + sequential inference proof inside.

2025년 12월 06일

Mamba beats Transformer with linear-time complexity using Selective State Space Models. See the selection mechanism that makes it work.

2025년 12월 04일

DeepSeek-V3 matches GPT-4o with 671B parameters but activates only 37B. The MoE, MLA, and load balancing techniques that made it possible.