collaborators

6 papers

cs.LG2026

Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently

Stanley Wei, Juno Kim

Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains in reasoning performance at…

cs.LG2026

Mirror Mean-Field Langevin Dynamics

Anming Gu, Juno Kim

The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over , and has gained attention recently…

math.OC2025

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points

Naoya Yamamoto, Juno Kim, Taiji Suzuki

Wasserstein gradient flow (WGF) is a common method to perform optimization over the space of probability measures. While WGF is guaranteed to converge to a first-order stationary p…

cs.LG2025

Transformers Provably Solve Parity Efficiently with Chain of Thought

Juno Kim, Taiji Suzuki

This work provides the first theoretical analysis of training transformers to solve complex problems by recursively generating intermediate states, analogous to fine-tuning for cha…

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…

stat.ML2025

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression

Juno Kim, Dimitri Meunier, Arthur Gretton +2

We provide a convergence analysis of deep feature instrumental variable (DFIV) regression (Xu et al., 2021), a nonparametric approach to IV regression using data-adaptive features…