Author

Dong-Jae Lee

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Calibration-Free Early Stopping for Chain-of-Thought Reasoning via E-processes

Reasoning large language models (LLMs) benefit from test-time scaling, motivating adaptive policies that spend tokens when they help and stop early otherwise. Existing rules halt when a confidence or stability signal crosses a threshold, but such thresholds rarely transfer across models and datasets, and validation-cal...

Dong-Jae Lee, Gyojin Han, Junmo Kim · 0 citations

#artificial intelligence Preprint Sep 2026

Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

Direct Diversity Optimization is presented, an offline post-training method that combines Divergence-Tree Collection with the Reference-Relative Target-Odds Objective (RTO) and achieves the strongest task success and successful strategy coverage among the compared post-training methods across BabyAI, BabaIsAI, and WebS...

Junwon Ko, Dong-Jae Lee, Minchan Kwon et al. · 0 citations

#artificial intelligence Apr 2026

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

This paper proposes a novel training free token pruning framework grounded in the dual form perspective of attention, and derives a novel metric quantifying both a token's information magnitude and information duplication.

Dong-Jae Lee, S. Baek, Junmo Kim · arXiv.org · 0 citations