by Chuyuan Fu Papers
3 papers found
Conference
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
Connor Schenck, Isaac Reid, Mithun Jacob et al.
ICML 2025spotlightarXiv:2502.02562
13
citations
Vision Language Models are In-Context Value Learners
Yecheng Jason Ma, Joey Hejna, Chuyuan Fu et al.
ICLR 2025oralarXiv:2411.04549
49
citations
RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
Jiayuan Gu, Sean Kirmani, Paul Wohlhart et al.
ICLR 2024spotlightarXiv:2311.01977
119
citations