3 papers
cs.RO2026
DeCo: Task Decomposition and Skill Composition for Zero-Shot Generalization in Long-Horizon 3D Manipulation
Zixuan Chen, Junhui Yin, Yangtao Chen +6
Generalizing language-conditioned multi-task imitation learning (IL) models to novel long-horizon 3D manipulation tasks is challenging. To address this, we propose DeCo (Task Decom…
cs.LG2026
Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching
Jiacheng Cheng, Xu Zhang, Guanghui Qiu +3
Federated Learning (FL) enables collaborative training across decentralized data, but faces key challenges of bidirectional communication overhead and client-side data heterogeneit…
cs.CV2025
PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
Zixin Zhang, Kanghao Chen, Xingwang Lin +6
The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligen…