Publications

Selected publications from the lab and collaborators.

Generative Adversarial Loops

Kislay Aditya Oj, Nidhi Jain, Sri Surya Varma Datla, Priyanka Jayaswal, Kumar Krishna Agrawal, Aditya Desai · arXiv preprint · 2026

Inference time context sparsity: Illusion or opportunity?

Sahil Joshi, Prithvi Dixit, Agniva Chowdhury, Anshumali Shrivastava, Joseph E. Gonzalez, Ion Stoica, Kumar Krishna Agrawal, Aditya Desai · arXiv preprint · 2026

Shepherd: Pattern-Guided Trajectory Selection for Coding Agents on SWE-Bench

Alejandro Cuadron, Aditya Desai, Luis Gaspar Schroeder, Xingyao Wang, Wenjie Ma, Dacheng Li, Yichuan Wang, Ion Stoica, Graham Neubig, Joseph E. Gonzalez · 2026

SOCKET: Soft Collision Kernel Estimator for Sparse Attention

Sahil Joshi, Agniva Chowdhury, Wyatt Bellinger, Amar Kanakamedala, Ekam Singh, Hoang Anh Duy Le, Aditya Desai, Anshumali Shrivastava · arXiv preprint · 2026

Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity

Sahil Joshi, Prithvi Dixit, Aryan Katiyar, Agniva Chowdhury, Joseph E. Gonzalez, Anshumali Shrivastava, Aditya Desai, Kumar Krishna Agrawal · arXiv preprint · 2026

vAttention: Verified sparse attention via sampling

Aditya Desai, Kumar Agrawal, Shuo Yang, Alejandro Cuadron Lafuente, Luis Gaspar Schroeder, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica · ICLR 2026 · 2026

vCache: Verified Semantic Prompt Caching

Luis Gaspar Schroeder, Aditya Desai, Alejandro Cuadron Lafuente, Kyle Chu, Shu Liu, Mark Zhao, Stephan Krusche, Alfons Kemper, Matei Zaharia, Joseph E. Gonzalez · ICLR 2026 · 2026

Barbarians at the gate: How AI is upending systems research

Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Bowen Wang, Alex Krentsel, Tian Xia, Mert Cemri, Jongseok Park, Shuo Yang, et al. · arXiv preprint · 2025

Identity with Locality: An ideal hash for gene sequence search

Tianyi Zhang, Gaurav Gupta, Aditya Desai, Anshumali Shrivastava · KDD 2025 · 2025

Let the barbarians in: How AI can accelerate systems performance research

Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Shubham Agarwal, Mert Cemri, Bowen Wang, Alexander Krentsel, Tian Xia, Jongseok Park, et al. · arXiv preprint · 2025

The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks

Alejandro Cuadron, Dacheng Li, Wenjie Ma, Xingyao Wang, Yichuan Wang, Siyuan Zhuang, Shu Liu, Luis Gaspar Schroeder, Tian Xia, Huanzhi Mao, et al. · arXiv preprint · 2025

vAttention: Verified Sparse Attention

Aditya Desai, Kumar Krishna Agrawal, Shuo Yang, Alejandro Cuadron, Luis Gaspar Schroeder, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica · arXiv preprint · 2025

vCache: Verified semantic prompt caching

Luis Gaspar Schroeder, Aditya Desai, Alejandro Cuadron, Kyle Chu, Shu Liu, Mark Zhao, Stephan Krusche, Alfons Kemper, Matei Zaharia, Joseph E. Gonzalez · arXiv preprint · 2025

Elastic Parameter Memory for Efficient Machine Learning

Aditya Desai · PhD thesis, Rice University · 2024

HashAttention: Semantic sparsity for faster inference

Aditya Desai, Shuo Yang, Alejandro Cuadron, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica · arXiv preprint · 2024

HashOrder: Accelerating Graph Processing Through Hashing-based Reordering

Tianyi Zhang, Aditya Desai, Gaurav Gupta, Anshumali Shrivastava · 2024

IDentity with Locality: An ideal hash for gene sequence search

Aditya Desai, Gaurav Gupta, Tianyi Zhang, Anshumali Shrivastava · arXiv preprint · 2024

In defense of parameter sharing for model-compression

Aditya Desai, Anshumali Shrivastava · ICLR 2024 · 2024

Sketch to adapt: Fine-tunable sketches for efficient LLM adaptation

Tianyi Zhang, Junda Su, Aditya Desai, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava · arXiv preprint · 2024

SS1: Accelerating inference with fast and expressive sketch structured transform

Kimia Saedi, Aditya Desai, Apoorv Walia, Jihyeong Lee, Keren Zhou, Anshumali Shrivastava · NeurIPS 2024 · 2024

Hardware-aware compression with random operation access specific tile (ROAST) hashing

Aditya Desai, Keren Zhou, Anshumali Shrivastava · ICML 2023 · 2023

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random subspaces

Aditya Desai, Benjamin Meisburger, Zichang Liu, Anshumali Shrivastava · arXiv preprint · 2023

Scissorhands: Exploiting the persistence of importance hypothesis for LLM KV cache compression at test time

Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava · NeurIPS 2023 · 2023

Random Offset Block Embedding (ROBE) for compressed embedding tables in deep learning recommendation systems

Aditya Desai, Li Chou, Anshumali Shrivastava · MLSys 2022 · 2022

The trade-offs of model size in large recommendation models: A 10000x compressed Criteo-TB DLRM model (100 GB parameters to mere 10 MB)

Aditya Desai, Anshumali Shrivastava · NeurIPS 2022 · 2022