most citedLLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology

1 citations · 2 across the 5 of their papers we have counts for

collaborators

7 papers

cs.DC2025

A Distributed Framework for Causal Modeling of Performance Variability in GPU Traces

Ankur Lahiry, Ayush Pokharel, Banooqa Banday +5

Large-scale GPU traces play a critical role in identifying performance bottlenecks within heterogeneous High-Performance Computing (HPC) architectures. However, the sheer volume an…

cs.DC2025

Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant

Seth Ockerman, Amal Gueroudji, Song Young Oh +5

Vector databases have rapidly grown in popularity, enabling efficient similarity search over data such as text, images, and video. They now play a central role in modern AI workflo…

cs.DC20251 cited

LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology

Renan Souza, Timothy Poteet, Brian Etz +5

Modern scientific discovery increasingly relies on workflows that process data across the Edge, Cloud, and High Performance Computing (HPC) continuum. Comprehensive and in-depth an…

cs.DC20251 cited

PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows

Renan Souza, Amal Gueroudji, Stephen DeWitt +5

Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and pee…

cs.DC2025

PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training

Seth Ockerman, Amal Gueroudji, Tanwi Mallick +4

Spatiotemporal graph neural networks (ST-GNNs) are powerful tools for modeling spatial and temporal data dependencies. However, their applications have been limited primarily to sm…

cs.DC2025

Scalable GPU Performance Variability Analysis framework

Ankur Lahiry, Ayush Pokharel, Seth Ockerman +3

Analyzing large-scale performance logs from GPU profilers often requires terabytes of memory and hours of runtime, even for basic summaries. These constraints prevent timely insigh…