Orion Weller

Seq vs Seq: An Open Suite of Paired Encoders and Decoders

On the Theoretical Limitations of Embedding-Based Retrieval

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning

Rank1: Test-Time Compute for Reranking in Information Retrieval

MMTEB: Massive Multilingual Text Embedding Benchmark

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models