5 papers
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
Yihan Lin, Jiawei He, Shifeng Bao +6
Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAM…
Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds
Shaojun Xu, Xiaoling Zhou, Yihan Lin +4
Model-Based Reinforcement Learning yields sample efficiency via latent imagination, yet remains constrained by Historical Tethering: imagination is typically initialized from obser…
Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
Yapeng Meng, Lin Yang, Yuguo Chen +6
Motion blur arises when rapid scene changes occur during the exposure period, collapsing rich intra-exposure motion into a single RGB frame. Without explicit structural or temporal…
Quantitative evaluation of brain-inspired vision sensors in high-speed robotic perception
Taoyi Wang, Lijian Wang, Yihan Lin +4
Perception systems in robotics encounter significant challenges in high-speed and dynamic conditions when relying on traditional cameras, where motion blur can compromise spatial f…
Technical report of a DMD-based Characterization Method for Vision Sensors
Yapeng Meng, Taoyi Wang, Yihan Lin
This technical report presents a novel DMD-based characterization method for vision sensors, particularly neuromorphic sensors such as event-based vision sensors (EVS) and Tianmouc…