Scholar
Connor Watts
Google Scholar ID: 9zHWZFEAAAAJ
Member of Technical Staff
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
4
H-index
1
i10-index
0
Publications
3
Co-authors
0
Publications
5 items
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
2026
Cited
0
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
2026
Cited
0
Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
2026
Cited
0
Detecting and Characterizing Planning in Language Models
2025
Cited
0
Large language models can learn and generalize steganographic chain-of-thought under process supervision
2025
Cited
0
