作者位次 #2/3ICML 2026Poster· Deep Learning / Graph Neural Networks
Quantile-Free Uncertainty Quantification in Graph Neural Networks
Soyoung Park · Hwanjun Song · Sungsu Lim
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Soyoung Park · Hwanjun Song · Sungsu Lim
Doyoung Kim · Youngjun Lee · Joeun Kim · Jihwan Bang · Hwanjun Song · Susik Yoon · Jae-Gil Lee
Joeun Kim · Seunghyouk Yoon · Xuan-Bach Le · Youngeun Nam · Doyoung Kim · Hwanjun Song · Jae-Gil Lee
Retrieval-augmented generation(RAG) systems depend on retrieval modules to supply grounding evidence for large language models. While hybrid approaches combining sparse and dense retrievers improve performance, most rely on fixed weights that ignore query-specific and corpus-specific variation. S...
Hwanjun Song
Much of the alignment tuning literature is organized around optimization objectives, while the construction of alignment data is often treated implicitly. In this survey, we adopt a data centric perspective and reframe alignment tuning as a pipeline design problem. We decompose alignment data con...
Donghee Han · Daeyoung Roh · A Young Kim · Hwanjun Song · Mun Yong Yi
Large Language Models (LLMs) have shown remarkable potential in recommendation systems but suffer from prohibitive inference latency. Existing distillation approaches typically target Small Language Models (SLMs) or Conventional Recommendation Models (CRMs), face a critical trade-off between comp...
Taewon Yun · Jisu Shin · Jeonghwan Choi · Seunghwan Bang · Hwanjun Song
Distilling large reasoning models (LRMs) has become essential for making their Long-CoT reasoning capabilities practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches, which select complete reasoning traces post-hoc, overlook the collaborative po...