Julian Shun
Scholar

Julian Shun

Google Scholar ID: BGh9WU4AAAAJ
MIT
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
3,970
 
H-index
33
 
i10-index
66
 
Publications
20
 
Co-authors
0
 
Contact
CVOpen ↗
Publications
12 items
VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair
2026
Cited
0
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
2026
Cited
0
Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval
2025
Cited
0
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
2025
Cited
0
Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs
2025
Cited
0
CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search
2025
Cited
0
Practical and Accurate Local Edge Differentially Private Graph Algorithms
2025
Cited
0
Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning
2025
Cited
0
Resume
Background
  • Associate Professor in the Department of Electrical Engineering and Computer Science at MIT
  • Principal Investigator at the Computer Science and Artificial Intelligence Laboratory (CSAIL)
  • Interested in the theory and practice of parallel and high-performance computing
  • Works on designing efficient algorithms and data structures with strong theoretical guarantees and good empirical performance
  • Also designs high-level programming frameworks to help programmers write efficient parallel code more easily
  • Recent research interests include graph analytics, spatial and graph clustering, and dynamic algorithms