3.4k citations
- Microsoft (United States)US248 papers
- Massachusetts Institute of TechnologyUS63 papers
- University of WashingtonUS54 papers
- Carnegie Mellon UniversityUS52 papers
- University of California, BerkeleyUS50 papers
- University of CambridgeGB50 papers
- Stanford UniversityUS47 papers
- University of Science and Technology of ChinaCN39 papers
- Tsinghua UniversityCN37 papers
- Peking UniversityCN34 papers
- Google (United States)US33 papers
- University College LondonGB31 papers
1,400 papers
Towards Standardized Evaluation of GPU Memory Safety with GMSBench
Saurabh Singh, Jaewon Lee, Seonjin Na +1
As GPUs become increasingly integral to high-performance computing and machine learning, ensuring memory safety in GPU programs has become crucial for reliable and secure execution…
Conformal Prediction for Offensive Security
Giovanni Cherubin
Despite its introduction more than a quarter century ago, Conformal Prediction (CP) has seen surprisingly few applications to the cyber security world thus far. In particular, we o…
Aker: Density-Aware Approximate Caching for Vector Search (Extended Version)
Sukjoon Oh, Minki Kang, Dohyun Kim +5
Disk-based approximate nearest neighbor search (ANNS) incurs high I/O overhead due to frequent disk accesses during index traversal. Approximate caching, which reuses the results o…
A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformations
Hasan Najib Mahmud, Shreya Gupta, Isha Chaudhary +4
AI code agents are increasingly deployed to resolve real software issues, yet their reliability under superficial code variations remains poorly understood. We evaluate whether cod…
Evaluating Large Language Models for Antisemitic Incident Classification
Karina Halevy, Julia Mendelsohn, Chan Young Park +2
Addressing hate and violence in society requires timely detection of hateful events from public reporting, but automated identification of hateful events remains underexplored. We…
Mandol: An Agglomerative Agent Memory System for Long-Term Conversations
Yuhan Zhang, Zhiyuan Guo, Ziheng Zeng +3
Long-term conversational agents need to remember and query cross-session, multi-typed information with complex correlations. Existing agent memory systems rely on heterogeneous vec…