7 papers
Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL
Minchan Kwon, Seunghee Koh, Sunghyun Baek +2
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 reinforcem…
PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting
Sungjae Choi, Seunghee Koh, Junmo Kim
Recent advancements in 3D Gaussian Splatting (3DGS) have extended its capabilities to multi-scale segmentation. Existing methods reconstruct a scene with Gaussian primitives and le…
</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
Seunghee Koh, Sungjae Choi, Minchan Kwon +2
Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often produces long, redundant traces. Recent training-free early-exit methods shorten…
MDS-DETR: DETR with Masked Duplicate Suppressor
Chanho Lee, Seunghee Koh, Yunho Jeon +1
The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to a…
Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
Seunghee Koh, Sunghyun Baek, Youngdong Kim +1
Unlearning in large language models (LLMs) has emerged as a promising safeguard against adversarial behaviors. When the forgetting loss is applied uniformly without considering tok…
IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
Sunghyun Baek, Jaemyung Yu, Seunghee Koh +3
Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich repr…
Disposable Transfer Learning for Selective Source Task Unlearning
Seunghee Koh, Hyounguk Shon, Janghyeon Lee +2
Transfer learning is widely used for training deep neural networks (DNN) for building a powerful representation. Even after the pre-trained model is adapted for the target task, th…