2 papers
cs.RO2026
Learning to Absorb Corrections: Critic-Weighted Residual Flow for Vision-Based Insertion
Yiqing Yuan, Zhi Li, Jinrong Yang +5
Vision-based insertion requires correcting alignment errors while retaining useful behavior learned from demonstrations. We present ACT--Flow, an online learning framework that cou…
cs.RO2026
Unordered Landmark Visual Navigation
Hao Ren, Junzhe Zhu, Yihan Li +8
Image-goal navigation is a fundamental capability for embodied AI, yet its practical deployment is strained by strong prior assumptions. Existing methods predominantly rely on temp…