Mayank Mishra
Source-listed: Graduate Student Researcher (GSR) and PhD student · University of California, Berkeley
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language ModelingSaved credit: First author · 2026Explore people connected to this work →
- Granite Code Models: A Family of Open Foundation Models for Code IntelligenceSaved credit: First author · 2024Explore people connected to this work →
- StarCoder: may the source be with you!Saved credit: Contributor · 2023Explore people connected to this work →
- Reducing Transformer Key-Value Cache Size with Cross-Layer AttentionSaved credit: First author · 2024Explore people connected to this work →
- Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlappingSaved credit: First author · 2025Explore byline and saved connections →