Sara Hooker

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

The Disparate Impacts of Speculative Decoding

One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers

Aya Vision: Advancing the Frontier of Multilingual Multimodality

Verification Limits Code LLM Training

Aya Vision: Advancing the Frontier of Multilingual Multimodality

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

MMTEB: Massive Multilingual Text Embedding Benchmark

Bridging the Data Provenance Gap Across Text, Speech, and Video

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers

Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress

To Code or Not To Code? Exploring Impact of Code in Pre-training

Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts