Jeremy Yang
papers
pplx-embed-v2-late technical report [blog] [model]
Markus Krimmel, Louis Milliken, Ekaterina Glazkova, Maximilian Schall, Antoine Chaffin, Sedigheh Eslami, Jonas Golde, Denis Bykov, Claire Beamer, Jeremy Yang, Bo Wang
WANDR: A benchmark for wide and deep research [blog] [data]
Vitalii Polshkov, Marcin Pitera, Jeremy Yang, Kirill Priemko, Maksim Gaiduk, Aleks Nikolenko, Denis Bykov, Denis Yarats, Clare Southern, Jerry Ma
How AI agents reshape knowledge work: Autonomy, efficiency, and scope [blog] [summary] [HBR]
Jeremy Yang, Kate Zyskowski, Noah Yonack, Jerry Ma
DRACO: A cross-domain benchmark for deep research accuracy, completeness, and objectivity [blog] [data]
Joey Zhong, Hao Zhang, Clare Southern, Jeremy Yang, Thomas Wang, Kate Jung, Shu Zhang, Denis Yarats, Johnny Ho, Jerry Ma
The adoption and usage of AI agents: Early evidence from Perplexity [blog] [summary]
Jeremy Yang, Noah Yonack, Kate Zyskowski, Denis Yarats, Johnny Ho, Jerry Ma
blogs
In collaboration with the team.
A good teacher meets the student where they are
Building shared workspaces for people and agents
Multimodal embeddings beyond a single vector
Contextual embedding beyond the gold passage
Photon: Building a retrieval and ranking engine from scratch
Learning from real-world experience
CobbleDB: Rebuilding AI search storage for lower latency and cost
Q2D-Web: Evaluating first-stage retrievers at scale
Optimizing on-device inference for Apple Silicon
A local-first agent for private and cost-effective knowledge work
Brain: Agentic memory as a knowledge wiki
Making SPACE: Secure and efficient runtimes for long-running agents
WANDR benchmark: Evaluating research agents that must search wide and deep
How AI agents reshape knowledge work
Evaluating deep research performance in the wild with the DRACO benchmark