Get started
Author

Kevin O'Sullivan

Observed name: O'Sullivan, Kevin
Observed institutions: ETH Zurich, SystemsX.ch
OpenAlex ID: A5126271177
Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
2026 · Guiu, Alex Martí, Zumarraga, Nicolas, et al. · arXiv (Cornell University)
PDF
Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
2026 · Strand, Lasse B., Jakob, Robert, et al. · arXiv (Cornell University)
PDF
TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models
2026 · Maritsch, Martin, Stoffregen, Timo, et al. · arXiv (Cornell University)
PDF
Event History Over Scale: Compact Transformers for Low-Latency Limit Order Book Forecasting
2026 · Schaurecker, David, Strand, Lasse B., et al. · arXiv (Cornell University)
PDF
ConRAG: Lightweight inference of multi-hop relations
2026 · Bänziger, Kilian, Laguna, Sonia, et al. · arXiv (Cornell University)
PDF
AuscuTSLM: Patient-Level Multimodal Question Answering from Multi-Site Auscultation Recordings
2026 · Wu, Fan, Wang, Tsai-Ning, et al. · Repository for Publications and Research Data (ETH Zurich)
RestoreBench: Can AI Agents Restore Power Flow Convergence?
2026 · Mansutti, Riccardo, Pomarico, Andrea, et al. · arXiv (Cornell University)
PDF
TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series
2026 · Zumarraga, Nicolas, Steno, Lorenzo, et al. · arXiv (Cornell University)
PDF
Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections
2026 · Peters, Baran, Hollbeck, Gabor, et al. · arXiv (Cornell University)
PDF
Patient-Level Multimodal Question Answering from Multi-Site Auscultation Recordings
2026 · Wu, Fan, Wang, Tsai-Ning, et al. · arXiv (Cornell University)
PDF
Calibrate Globally, Measure Everywhere: Scaling LLM-Based Prevalence Measurement Across A/B Experiments
2026 · Xu, Zehao, Paek, Tony, et al. · arXiv (Cornell University)
PDF
Decision Quality Evaluation Framework at Pinterest
2026 · Tian, Yuqi, Paine, Robert, et al. · arXiv (Cornell University)
PDF
TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning
2026 · Zumarraga, Nicolas, Kaar, Thomas, et al. · arXiv (Cornell University)
PDF
TS-Haystack: A Multi-Scale Retrieval Benchmark for Time Series Language Models
2026 · Zumarraga, Nicolas, Kaar, Thomas, et al. · Repository for Publications and Research Data (ETH Zurich)
How User Approval and Cognitive Load Shape the Effectiveness of a Digital Swap Nudge
· Manzke, Leonie, O'Sullivan, Kevin, et al. · Journal of the Association for Information Systems
PDF
Works count: 15
Citation count:
H-index:
I10-index:
Year
Topic
Type