Get started
Author

Alex Cloud

Language models transmit behavioural traits through hidden signals in data
2026 · Alex Cloud, Minh Le, et al. · Nature · 9
PDF
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
2025 · Cloud, Alex, Le, Minh, et al. · arXiv (Cornell University) · 4
PDF
Anticipatory Fictitious Play
2023 · Alex Cloud, Albert Wang, et al. · International Joint Conference on Artificial Intelligence · 2
PDF
Distillation Robustifies Unlearning
2025 · Bruce W, Lee, Addie Foote, et al. · neural information processing systems · 1
Gradient Routing Localizes and Removes Unintended Behaviors in RL
2026 · Ward, Jake, Hu, Shawn, et al. · arXiv (Cornell University)
PDF
Modular Pretraining Enables Access Control
2026 · Roland, Ethan, Cubuktepe, Murat, et al. · arXiv (Cornell University)
PDF
Recontextualization Mitigates Specification Gaming without Modifying the Specification
2025 · Azarbal, Ariana, Gillioz, Victor, et al. · arXiv (Cornell University)
PDF
Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
2025 · Shilov, Igor, Cloud, Alex, et al. · arXiv (Cornell University)
PDF
Output Supervision Can Obfuscate the Chain of Thought
2025 · Drori, Jacob, Marks, Luke, et al. · arXiv (Cornell University)
PDF
Distillation Robustifies Unlearning
2025 · Lee, Bruce W., Foote, Addie, et al. · arXiv (Cornell University)
PDF
Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
2024 · Cloud, Alex, Goldman-Wetzler, Jacob, et al. · arXiv (Cornell University)
PDF
Variance Decompositions for Extensive-Form Games
2021 · Alex Cloud, Eric B. Laber · IEEE Conference on Games (CoG)
PDF
Works count: 12
Citation count: 16
H-index: 2
I10-index:
Year
Topic
Type