Sepanta Zeighami
Scholar

Sepanta Zeighami

Google Scholar ID: vaf4fT8AAAAJ
UC Berkeley
DatabasesMachine Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
231
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
0
 
Contact
GitHubOpen ↗LinkedInOpen ↗
Publications
10 items
Semantic Data Processing with Holistic Data Understanding
2026
Cited
0
Can AI Agents Answer Your Data Questions? A Benchmark for Data Agents
2026
Cited
0
Arming Data Agents with Tribal Knowledge
2026
Cited
0
Task Cascades for Efficient Unstructured Data Processing
arXiv.org · 2026
Cited
1
Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees
2025
Cited
0
Multi-Objective Agentic Rewrites for Unstructured Data Processing
2025
Cited
0
Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees
2025
Cited
0
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
2025
Cited
0
Resume (English only)
Background
  • Postdoctoral Scholar at University of California, Berkeley, with a broad interest in data and AI systems, working on building accurate, reliable, and efficient data-centric systems, with a penchant for theoretically understanding the use of machine learning in such systems.
Co-authors
0 total
Co-authors: 0 (list not available)