Reconstructing Multi-Person Interactions via Semantic-Geometric Graph Optimization
Submitted to CVPR 2026. Multi-person interaction reconstruction via semantic-geometric graph optimization.
Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
Submitted to CVPR 2026. 3D foundation models as world model for coordinated bimanual manipulation.
RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies
arXiv 2025. First real-world benchmark for large-scale real-robot evaluation of embodied policies.
adina-yakefu
Hierarchical Semantic Conditioning for Pose-aware Object Manipulation
Submitted to ICRA 2026. 3D semantic representation for part-aware object manipulation.
Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-arm Collaboration Challenge at CVPR 2025 MEIS Workshop
arXiv 2025. Benchmarking generalizable bimanual manipulation in the RoboTwin challenge.
et-al.