collaborators

7 papers

cs.LG2026

Predicting LLM Reasoning Performance with Small Proxy Model

Woosung Koh, Juyoung Suk, Sungjun Han +2

Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up. However, this approach be…

cs.LG2026

Generative Visual Code Mobile World Models

Woosung Koh, Sungjun Han, Segyu Lee +2

Mobile Graphical User Interface (GUI) World Models (WMs) offer a promising path for improving mobile GUI agent performance at train- and inference-time. However, current approaches…

cs.CL2026

Multi-Drafter Speculative Decoding with Alignment Feedback

Taehyeon Kim, Hojung Jung, Se-Young Yun

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserve…

cs.LG2026

mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT

Woosung Koh, Jeyoung Jeon, Youngjin Song +4

Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally…

cs.LG2025

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners

Woosung Koh, Wonbeen Oh, Jaein Jang +7

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (…

cs.LG2025

FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL

Woosung Koh, Wonbeen Oh, Siyeol Kim +5

Multi-agent reinforcement learning has demonstrated significant potential in addressing complex cooperative tasks across various real-world applications. However, existing MARL app…