6 papers
Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement
Wenbo Huang, Jianxin Bi, Shunyu Yang +10
Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks. Several recent works expose the benchmark's success criteria to the lea…
One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns
Yiyang Fu, Zihao Huang, Dongchen Han +4
Large language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interactions, however, compute deman…
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
Shukai Gong, Xuanran Zhai, Yintianrun Zhang +16
Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing worl…
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Juncheng Ma, Jianxin Bi, Yufan Deng +19
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remai…
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
Yiyang Fu, Chubin Zhang, Shukai Gong +7
It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-Language-Action (VLA) models…
TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
Shukai Gong, Yiyang Fu, Fengyuan Ran +2
We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By ide…