Keshav Santhanam
Source-listed: Core contributor to Inference and Software Support · NVIDIA
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Holistic Evaluation of Language ModelsSaved credit: Contributor · 2022Explore people connected to this work →
- DSPy: Compiling Declarative Language Model Calls into Self-Improving PipelinesSaved credit: Contributor · 2023Explore people connected to this work →
- ColBERTv2: Effective and Efficient Retrieval via Lightweight Late InteractionSaved credit: Contributor · 2022Explore people connected to this work →
- PLAID: An Efficient Engine for Late Interaction RetrievalSaved credit: Contributor · 2022Explore people connected to this work →
- Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer ModelsSaved credit: Contributor · 2025Explore people connected to this work →