Picomp-Lab
Oregon State University. 1500 SW Jefferson Way, Corvallis, OR 97331.
CASE 3067
110 SW Park Terrace
Corvarllis, Oregon
The Parallel Intelligent Computing (Picomp) Lab at the EECS at Oregon State University focuses on the study of large-scale parallel systems and artificial intelligence. We focus on developing scalable algorithms, efficient system designs, and innovative machine learning techniques to address complex, real-world problems. Our mission is to improve the performance, reliability, energy efficiency, and productivity of large-scale parallel systems, contributing to advancements in computational science, engineering, and data-driven scientific discovery.
news
| Feb 28, 2026 | A paper “Evaluating LLM Coding Agents on SZ-Family Lossy Compression Across Architectures” is accepted in IPDPS HPAI4S’26. |
|---|---|
| Feb 24, 2026 | A paper “FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving” is accepted in ACM International Conference on Supercomputing (ICS’26). |
| Dec 29, 2025 | A paper “LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation” is accepted in IPDPS’26. |
| Sep 16, 2025 | Two Ph.D. students, Arunavo Dey and Changqing Li, are joining us this fall! |
| Sep 12, 2025 | A paper “Phoenix: Enabling Unstructured Sparse Fine-Tuning and Inference for Foundation Models on Wafer-Scale Engine” is accepted in SC’25 ExHetAI workshop. |