Victoria Lin

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Victoria Lin is a Research Scientist at Meta AI, where she is dedicated to creating technologies that empower humans to tackle complex, knowledge-intensive challenges. Her recent work focuses on efficient and sparse architecture design for multimodal foundation models, long-range memory and retrieval augmentation. She received her Ph.D. in Computer Science from the Paul G. Allen School at the University of Washington.

Personal Website

Google Scholar

Twitter

Research Areas

Natural Language Processing (NLP)

Ranking & Recommendations

Victoria's Work

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, an...

Few-shot Learning with Multilingual Generative Language Models

Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be...

RA-DIT: Retrieval-Augmented Dual Instruction Tuning

Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from exter...

MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed for pre-training mixed-modal, ear...

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution

Large language models (LLMs) often hallucinate and lack the ability to provide attribution for their generations. Semi-par...

OPT: Open Pre-trained Transformer Language Models

Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabiliti...

Victoria's Publications

April 25, 2025

RESEARCH

NLP

ReasonIR: Training Retrievers for Reasoning Tasks

Rulin Shao, Qiao Rui, Varsha Kishore, Niklas Muennighoff, Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Scott Yih, Pang Wei Koh, Luke Zettlemoyer