Scholar

Neil Kale

Google Scholar ID: OrQXY9sAAAAJ

Carnegie Mellon University

Machine LearningAI SafetyML for Healthcare

Google Scholar↗

Citations & Impact

All-time

Citations

78

H-index

3

i10-index

2

Publications

8

Co-authors

0

Contact

No contact links provided.

Publications

5 items

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders

2026

Cited

0

Mitigating Modal Imbalance in Multimodal Reasoning

2025

Cited

0

Reliable Weak-to-Strong Monitoring of LLM Agents

2025

Cited

0

Membership Inference Attacks for Unseen Classes

2025

Cited

0

Position: LLM Unlearning Benchmarks are Weak Measures of Progress

arXiv.org · 2024

Cited

5

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)