5 papers
STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models
Yichen Guo, Tinghao Wang, Qizhe Zhang +15
Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose substantial computational overhead,…
Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation
Yijie Xu, Haopeng Jin, Run Zhou +8
Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states. Reinforcement learning can r…
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation
Peterson Co, Sicheng Hu, Chunxuan Jiao +17
Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation. Realizing this prom…
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
Shuyi Zhang, Yunfan Lou, Hongyang Cheng +8
Vision-Language-Action (VLA) models are often constrained by the imitation ceiling imposed by sub-optimal data. While Reinforcement Learning (RL) fine-tuning can surpass this limit…
Data-Driven MPC with Data Selection for Flexible Cable-Driven Robotic Arms
Huayue Liang, Yanbo Chen, Hongyang Cheng +5
Flexible cable-driven robotic arms (FCRAs) offer dexterous and compliant motion. Still, the inherent properties of cables, such as resilience, hysteresis, and friction, often lead…