LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often described as in-context reinforcement learning (ICRL). Whether in-context learning (ICL) can actually play the role of RL, however, has not been tested. We study this questio...
Minchan Kwon, Seunghee Koh, Sunghyun Baek et al.· 0 citations
Transformer-based models have recently achieved strong performance on 3D reconstruction from images, and recent works extend them to process video streams in an online manner for real-world deployment. However, existing methods overlook two key signals when handling long image streams: the importance of each incoming f...
Sunghyun Baek, Hannah Bae, Minchan Kwon et al.· 0 citations
PePESeg3D achieves state-of-the-art performance in both multi-scale segmentation and scene reconstruction, highlighting the importance of integrating perception priors into both geometry optimization and feature learning for accurate multi-scale 3D segmentation.
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
Across four LRMs, five benchmarks, and two early-exit methods, increasing attention to the injected EoT reduces spurious CoT termination and answering-phase length, and reveals a limitation of controlling LRMs by externally matching their explicit think-block format.
Seunghee Koh, Su-Zie Choi, Minchan Kwon et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.