1 citations · 1 across the 7 of their papers we have counts for
8 papers
Continually Post-training Small Models via Synthetic Self-distillation
Woosung Koh, Hyunsoo Lee, Kyungjae Lee +4
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. While Self-Distillation Fine-Tunin…
Language Models Can Control Their Own Attention
Namgyu Ho, Huzama Ahmad, Woosung Koh +3
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If the user asks about a previou…
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…
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…
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…
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 (…
: Scalable Auto-Feedback for LLM-based Chart Generation
Woosung Koh, Jang Han Yoon, MinHyung Lee +7
Generating high-quality charts with Large Language Models (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $\langle \…
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…