collaborators

5 papers

cs.LG2026

Robust Domain Generalization under Divergent Marginal and Conditional Distributions

Jewon Yeom, Kyubyung Chae, Hyunggyu Lim +3

Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations und…

cs.LG2026

Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation

Seonghyeon Park, Jewon Yeom, Jaewon Sok +3

Quantifying uncertainty in Large Language Models (LLMs) is essential for mitigating hallucinations and enabling risk-aware deployment in safety-critical tasks. However, estimating…

cs.CL2026

Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning

Jaewon Sok, Jewon Yeom, Seonghyeon Park +2

Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant…

cs.CL2026

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs

Jewon Yeom, Jaewon Sok, Seonghyeon Park +2

Improving the reasoning abilities of large language models (LLMs) has largely relied on iterative self-training with model-generated data. While effective at boosting accuracy, exi…

cs.CL2025

"Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection Decoding

Hyunbin Jin, Je Won Yeom, Seunghyun Bae +1

Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot chain-of-thought (CoT) prompting. While effective, these methods require…