3 papers
cs.CV2026
Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data
Takaki Yamamoto, Chihiro Noguchi, Toshihiro Tanizawa
Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. W…
cs.RO2026
Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments
Chihiro Noguchi, Takaki Yamamoto
End-to-end (E2E) autonomous driving models that take only camera images as input and directly predict a future trajectory are appealing for their computational efficiency and poten…
cs.CV2025
From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction
Chihiro Noguchi, Takaki Yamamoto
Accurate perception of the surrounding environment is essential for safe autonomous driving. 3D occupancy prediction, which estimates detailed 3D structures of roads, buildings, an…