Kyungmin Kim

Harness-aware post-training can drastically improve LLM agent performance, especially when facing shifting tool environments, revealing a key design dimension often overlooked in AI systems.

Formal verification of robot safety can now be achieved without compromising the expressive power of foundation models, thanks to a novel modular architecture.

Guaranteeing uncertainty quantification in dynamic environments is now possible even when feedback is strategically withheld by an adversary.

Optimal transport provides a surprisingly tight and efficiently computable bound on transductive generalization in graph node classification, revealing how GNN depth impacts representation geometry.