Jiahai Feng

According to our database, Jiahai Feng authored at least 10 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Learning a Generative Meta-Model of LLM Activations.

Grace Luo, Jiahai Feng, Trevor Darrell, Alec Radford, Jacob Steinhardt

CoRR, February, 2026

2025

LLM Layers Immediately Correct Each Other.

Arjun Patrawala, Jiahai Feng, Erik Jones, Jacob Steinhardt

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts.

Jiahai Feng, Stuart Russell, Jacob Steinhardt

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Monitoring Latent World States in Language Models with Propositional Probes.

Jiahai Feng, Stuart Russell, Jacob Steinhardt

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Cognitively Inspired Interpretability in Large Neural Networks.

Anna Leshinskaya, Taylor W. Webb, Ellie Pavlick, Jiahai Feng, Gustaw Opielka, Claire E. Stevenson, Idan A. Blank

Proceedings of the 47th Annual Meeting of the Cognitive Science Society, 2025

2024

Learning Grounded Action Abstractions from Language.

Lionel Wong, Jiayuan Mao, Pratyusha Sharma, Zachary S. Siegel, Jiahai Feng, Noa Korneev, Joshua B. Tenenbaum, Jacob Andreas

Proceedings of the Twelfth International Conference on Learning Representations, 2024

How do Language Models Bind Entities in Context?

Jiahai Feng, Jacob Steinhardt

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Learning adaptive planning representations with natural language guidance.

Lionel Wong, Jiayuan Mao, Pratyusha Sharma, Zachary S. Siegel, Jiahai Feng, Noa Korneev, Joshua B. Tenenbaum, Jacob Andreas

CoRR, 2023

2022

Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks.

Katherine M. Collins, Catherine Wong, Jiahai Feng, Megan Wei, Josh Tenenbaum

Proceedings of the 44th Annual Meeting of the Cognitive Science Society, 2022

2020

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity.

Silviu-Marian Udrescu, Andrew K. Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020