Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing

CVPR 2025 Preserve or Modify? Context-Aware Evaluationfor Balancing Preservation and Modification in Text-Guided Image Editing Yoonjeon Kim, Soohyun Ryu, Yeonsung Jung, Hyunkoo Lee, Joowon Kim, June Yong Yang, Jaeryong Hwang, Eunho Yang  The development of vision-language and gen...

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

ICLR 2025 Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation  Byungjai Kim, Chanho Ahn, Wissam J. Baddar, Kikyung Kim, HUIJIN LEE, Saehyun Ahn, Seungju Han, Sungjoo Suh, Eunho Yang  Test-time adaptation updates pretrained models on the fly to handle...

Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models

ACL 2025 Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models  Kyeonghyun Kim, Jinhee Jang, Juhwan Choi, Yoonji Lee, Kyohoon Jin, YoungBin Kim  Large language models (LLMs) are renowned for their extensive linguistic knowledge and...

Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models

ACL 2025 Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models  Seunguk Yu, Juhwan Choi, Youngbin Kim  Despite the recent strides in large language models, studies have underscored the existence of social biases within ...

DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values

ICML 2025 Workshop on Actionable Interpretability (ICMLW-AIW) DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values Changhun Kim, Yechan Mun, Sangchul Hahn, Eunho Yang  This study proposes DeltaSHAP, a novel explainable artificial ...

Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing

CVPR 2025 Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modificationin Text-Guided Image Editing Yoonjeon Kim, Soohyun Ryu, Yeonsung Jung, Hyunkoo Lee, Joowon Kim, June Yong Yang, Jaeryong Hwang, Eunho Yang  The development of vision-language and gen...

Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy

CVPR 2025 Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy Joonhyun Jeong, Seyun Bae, Yeonsung Jung, Jaeryong Hwang, Eunho Yang  Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize a...

LANTERN++: Enhanced Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models

ICLR 2025 Workshop on Scalable Optimization for Efficient and Adaptive Foundation Models (ICLRW-SCOPE) (Oral) LANTERN++: Enhanced Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models Sihwan Park, Doohyuk Jang, Sung-Yub Kim, Souvik Kundu, Eunho Yang&...

TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation

ICLR 2025 Workshop on XAI4Science: From Understanding Model Behavior to Discovering New Scientific Knowledge (ICLRW-XAI4Science) TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation Hyeongwon Jang, Changhun Kim, Eunho Yang  Recent explainable artif...

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models

ICLR 2025 Token-Supervised Value Modelsfor Enhancing Mathematical Problem-Solving Capabilities of Large Language Models  Jung Hyun Lee, June Yong Yang, Byeongho Heo, Dongyoon Han, Kyungsu Kim, Eunho Yang, Kang Min Yoo  With the rapid advancement of test-time compute sea...