Sotabase

Career

· Research Intern, Apple2021–
· Doctoral Researcher, Massachusetts Institute of Technology2021–
· GPU Performance And Modeling Intern, Samsung SARC | ACL2018–2018
· Research Assistant, University of California, Berkeley2018–2021
· Bachelor's degree, Computer Science, University of California, Berkeley2017–2021
· Research Assistant, University of California, Berkeley, Haas School of Business2017–2018

Publications (13)

Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
Conference on Machine Learning and Systems · 2019
232
cited
Self-Supervised Pretraining Improves Self-Supervised Pretraining
IEEE Workshop/Winter Conference on Applications of Computer Vision · 2021
129
cited
Integer-Only Zero-Shot Quantization for Efficient Speech Recognition
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2021
33
cited
Towards Verifiable Text Generation with Symbolic References
arXiv.org · 2023
23
cited
SageDB: An Instance-Optimized Data Analytics System
Proceedings of the VLDB Endowment · 2022
15
cited
Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition
arXiv.org · 2021
1
cited
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
2025
Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
2024
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
2024
Predicting Consumer Brand Recall and Choice Using Large-Scale Text Corpora
2018
Predicting Memory-Based Consumer Choices From Recall and Preferences
2018
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
2024
Striped Attention: Faster Ring Attention for Causal Transformers
2023
Sotabase
Aniruddha Nrusimha | Researcher Profile | Sotabase | Sotabase