Jian Kim — accepted AI-conference papers

2026

Learning Multi-View Spatial Reasoning from Cross-View Relations

Suchae Jeong, Jaehwi Song, Haeone Lee, Hanna Kim, Jian Kim, Dongjun Lee +6

CVPR 2026

Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems to understand 3D environments and manipulate objects across different viewpoints. In this work, we introduce Cross-View

Cited by 0 Source ↗Scholar ↗

2025

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making

Yejin Son, Minseo Kim, Sungwoong Kim, Seungju Han, Jian Kim, Dongju Jang +2

EMNLP 2025

Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these models fail. This obscures our understanding of embodied safet

Cited by 0 Source ↗PDF ↗Scholar ↗