A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse. Robot agents that act through code can already repair programs from execution feedback, yet it remains a central challenge to organize this...
Zi-Mo Wen, Yi-Jin Chen, Yuxuan Cao et al.· 10 citations· ⚡2
UMM-Reflection is introduced, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection tokens and th...
Yi-Jia Fan, Zi-Qi Huang, Zhongang Cai et al.· 0 citations
Across towel folding, book insertion, and Hanoi ring placement, LIFT learns faster and reaches higher performance than vision-only post-training, while ablations show that reactive force memory and online corrective data are both important for robust contact-rich manipulation.
Yi Wang, Wen-Di Chen, Zi-Mo Wen et al.· arXiv.org· 4 citations
Native unified modelling is position as a promising path towards systems that perceive, reason and create within a fully end-to-end framework through SenseNova-U1.5, an 8B-MoT native unified multimodal model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture.
Hai-Wen Diao, Jia-Hao Wang, Chen-Jing Ding et al.· 3 citations
Results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.
Boxiu Li, Zi-Mo Wen, Yi-Jia Fan et al.· 2 citations· ⚡1
The results show that careful tokenizer--backbone--system co-design can deliver strong high-resolution generation and editing within an efficient 4B model family.
