To appearInternational Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 2026
Collective communication is essential to high-performance computing and machine learning workloads, and exploiting sparsity in message payloads can reduce communication overhead.
Published in ACM Conference on AI and Agentic Systems (CAIS), 2026
As large language models continue to grow in size, distributed inference has become increasingly important.
Published in SPE Annual Technical Conference and Exhibition, 2025
This work describes how we built and evaluated EnergyLLM, a large language model for the energy domain.
Published in International Symposium on Experimental Algorithms, 2025
Cache-aware hierarchical rank/select data structure using Elias-Fano encoded L2 indices.
Published in SPE Annual Technical Conference and Exhibition, 2023
Grounding LLMs with industry content and a graph database.
Published in The Journal of Computing Sciences in Colleges, 2023
Generating hashcat rules for efficient password cracking. Awarded best research paper at CCSC Eastern.