Stories by fzliu

Beating Arc the Hard Way

Why are we using LLMs as calculators?

Code embedding model with Matryoshka learning and quantization-aware training

Evaluating Code Embeddings

ModernBERT

Code embedding model with Matryoshka learning and quantization-aware training

Evaluating Code Embeddings

Head-to-head benchmarking tool for embedding models

voyage-code-3

How do we evaluate vector-based code retrieval?

Are You a Peacetime CEO or a Wartime CEO? (2011)

Arctic-Embed 2.0: Multilingual Retrieval Without Compromise

Evaluating Code Embeddings

Head-to-head benchmarking tool for embedding models

Code embedding model with Matryoshka learning and quantization-aware training

A Better Way to Measure Progress in Semiconductors (2020)

Global AI Power Rankings

Evaluating Code Embeddings

2
3
4
5
6
7
8
9
10
11