3 papers
stat.ML2026
Sharp Capacity Thresholds in Linear Associative Memory: From Top-1 Retrieval to Tail-Average Learning
Nicholas Barnfield, Juno Kim, Eshaan Nichani +2
How many key-value associations can a linear memory store? The answer depends not only on the degrees of freedom in the memory matrix, but also on the retrieval c…
cs.LG2026
Coverage Improvement and Fast Convergence of On-policy Preference Learning
Juno Kim, Jihun Yun, Jason D. Lee +1
Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts…
cs.AI2025
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
Juno Kim, Denny Wu, Jason Lee +1
A key paradigm to improve the reasoning capabilities of large language models (LLMs) is to allocate more inference-time compute to search against a verifier or reward model. This p…