Get started
Author

Connor Watts

Observed name: Watts, Connor
OpenAlex ID: A5125653039
Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
2026 · Prasad, Aaditya Vikram, Watts, Connor, et al. · arXiv (Cornell University) · 9
PDF
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
2026 · Bergen, Leon, Bhalla, Usha, et al. · arXiv (Cornell University) · 4
PDF
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
2026 · Wolf, Lorenz, Watts, Connor, et al. · arXiv (Cornell University) · 3
PDF
Shaping & Monitoring Models through their Internal Representations
2026 · Fel, Thomas, Kowal, Matthew, et al. · arXiv (Cornell University)
PDF
Works count: 4
Citation count: 16
H-index: 3
I10-index:
Year
Topic
Type