collaborators

16 papers

cs.RO2026

CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving

Yunxiao Shi, Hong Cai, Mohammad Ghavamzadeh +1

End-to-end autonomous driving (E2E-AD) aims to directly map raw sensor information to driving actions. Recently, with the rapid advancement of multi-modal large language models (ML…

cs.CV2026

RoCA: Robust Cross-Domain End-to-End Autonomous Driving

Rajeev Yasarla, Shizhong Han, Hsin-Pai Cheng +7

End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deploym…

cs.RO2026

MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving

Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng +9

Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional im…

cs.CV2026

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

Tao Lin, Yuxin Du, Jiting Liu +14

Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often s…

cs.CV2026

CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers

Zhuojin Li, Hsin-Pai Cheng, Hong Cai +2

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce C…

cs.CV2026

FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices

Shizhong Han, Hsin-Pai Cheng, Hong Cai +3

Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resource-constrained edge devices, due…