Featured Posts
-
NeRF - Review
Diving into NeRF
-
DPO - Review
Reviewing DPO, a simpler way to fine-tune LLMs without explicitly modeling rewards
-
RoFormer(RoPE) - Review
Reviewing the RoFormer paper
-
Are You Smarter Than an LLM?
A firsthand experience with the MMLU benchmark
-
Mamba - Review
Reviewing the Mamba paper, replacing attention with linear-time sequence modeling
-
Structured State Spaces (S4) – Review
Reviewing the S4 paper