4 papers
QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
Yifan Ruan, Chenyang Cao, Andreas Burger +7
Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy…
Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
Jinhyeok Jang, Jaehong Kim, Jung Uk Kim
Pre-trained weights have become a cornerstone of modern deep learning, enabling efficient knowledge transfer and improving downstream task performance, especially in data-scarce sc…
Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired
ByungOk Han, Woo-han Yun, Beom-Su Seo +1
Guide dog robots offer promising solutions to enhance mobility and safety for visually impaired individuals, addressing the limitations of traditional guide dogs, particularly in p…
A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM
ByungOk Han, Jaehong Kim, Jinhyeok Jang
Vision-Language-Action (VLA) models are receiving increasing attention for their ability to enable robots to perform complex tasks by integrating visual context with linguistic com…