From the 1 of 5 linked papers with an AI index.
5 papers
A Model-Free Universal AI
Yegon Kim, Juho Lee
The paper proposes AIQI, a model-free reinforcement learning agent that uses universal induction over action-value functions and is proven to be asymptotically epsilon-optimal.
Mitigating Legibility Tax with Decoupled Prover-Verifier Games
Yegon Kim, Juho Lee
As large language models become increasingly capable, it is critical that their outputs can be easily checked by less capable systems. Prover-verifier games can be used to improve…
Parallel Test-Time Scaling with Multi-Sequence Verifiers
Yegon Kim, Seungyoo Lee, Chaeyun Jang +2
Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it i…
Active Learning with Selective Time-Step Acquisition for PDEs
Yegon Kim, Hyunsu Kim, Gyeonghoon Ko +1
Accurately solving partial differential equations (PDEs) is critical to understanding complex scientific and engineering phenomena, yet traditional numerical solvers are computatio…
Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision
Chaeyun Jang, Moonseok Choi, Yegon Kim +2
Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has…