Stories by fzliu

China's Data Center Boom: A View from Zhangjiakou (2025)

voyage-multimodal-3.5: a new multimodal retrieval frontier with video support

Are Pre-Trained Convolutions Better Than Pre-Trained Transformers? (2021)

PaperBanana: Automating Academic Illustration for AI Scientists

NumPy in C (2014)

voyage-multimodal-3.5: a new multimodal embedding frontier with video support

Voyage-multimodal-3.5: A new multimodal retrieval frontier with video support

The Legal Embedding Benchmark (MLEB)

Token-Count-Based Batching: Faster, Cheaper Embedding Inference for Queries

voyage-multimodal-3.5: a new multimodal retrieval frontier with video support

The Voyage 4 model family: shared embedding space with MoE architecture

Token-Count-Based Batching: Faster, Cheaper Embedding Inference for Queries

The Case Against LLMs as Rerankers

Ultra-Wide Band: A Transformational Technology for the Internet of Things

Token-Count-Based Batching: Faster, Cheaper Embedding Inference for Queries

Mapping China's Surnames

Token-Count-Based Batching: Faster, Cheaper Embedding Inference for Queries

How geometry is fundamental for chess

Nimzo – Grischuk Gambit

Threatening AI models has no meaningful effect on performance

1
2
3
4
5
6
7
8
9
10