Efficient Visual Token Compression for 3D Question Answering
ICML Workshop on efficient multimodal question answering (ICMLw), Jul. 2026.
Changwoo Baek*, Kyeongbo Kong†
Mitigating Visual Hallucinations for Reliable Multimodal Agents
ICML Workshop on Agents in the Wild: Safety, Security, and Beyond (ICMLw), Jul. 2026.
Sohyeon Kim*, Sang Yeon Yoon, Kyeongbo Kong†
Failure-Aware Query Refinement for Reliable Open-Vocabulary Home-Robot Perception
ICML Workshop on Agents in the Wild: Safety, Security, and Beyond (ICMLw), Jul. 2026.
Daun Jeong*, Sohyeon Kim*, Jouwon Song, Kyeongbo Kong†
Attention Weight Decomposition for Vision Model Compression
ICML Workshop on Weight-Space Symmetries: from Foundations to Practical Applications (ICMLw), Jul. 2026.
Hyunwoo Yu*, Yubin Cho*, Kyeongbo Kong†, Suk-Ju Kang†
Compositional Agentic Formulation Search for Open-Vocabulary Audio-Visual Event Localization
ICML Workshop on Compositional Learning: Safety, Interpretability, and Agents (ICMLw), Jul. 2026.
Beomgwon Jo*, Sunchan Park*, Kyeongbo Kong†
HYBRIDKV: Exploiting Head-Dominant Reconstruction for Efficient Query-Agnostic KV Cache Compression
ICML Workshop on AdaptFM: Resource-Adaptive Foundation Model Inference (ICMLw), Jul. 2026.
Changwoo Baek*, Kyeongbo Kong†
SFPruner: Single-Forward Visual Token Subset Selection for Resource-Efficient Multimodal Foundation Model Inference
ICML Workshop on AdaptFM: Resource-Adaptive Foundation Model Inference (ICMLw), Jul. 2026.
Jouwon Song*, Woohyeong Kim, Seungjae Baek, Kyeongbo Kong†
Reducing Attention Distribution Error with Unified Tail Aggregation for Sparse Attention
ICML Workshop on AdaptFM: Resource-Adaptive Foundation Model Inference (ICMLw), Jul. 2026.
Hyunwoo Yu*, Jongbeom Lee, Jaemin Choi, Jincheol Yang, Yubin Cho, Joonsik Nam, Seunghun Moon, Jung-Woo Chang, Bongjoon Hyun, Kyomin Sohn, Kyeongbo Kong†, Suk-Ju Kang†