QuoVLA: Quotient Space for Vision-Language-Action Models
About
Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and language instructions to continuous actions. Existing approaches typically take an action-insufficiency view, assuming that pretrained VLM latents either lack directly usable action information or should be shielded from action-learning signals. Against this view, our \textit{Quotient Theory for VLA} shows that pretrained VLM latents are not action-insufficient but action-sufficient: they already contain the information needed for control, yet remain overcomplete by distinguishing prompt-level variations that induce the same optimal action behavior. To operationalize this theory, we propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations. Specifically, QuoVLA instantiates this principle with a quantization module and a dual-branch design with relative temporal-complexity regularization, preserving action-relevant information while removing prompt-level redundancy. Extensive experiments across multiple benchmarks demonstrate that QuoVLA achieves strong performance, with particularly notable improvements in generalization under visual, linguistic, and environmental distribution shifts. Our code will be made publicly available.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Robotic Manipulation | LIBERO 1.0 (test) | Long98.7 | 57 | |
| Robotic Manipulation | LIBERO-Plus (test) | Language Robustness Score88.2 | 32 | |
| Robotic Manipulation | RoboTwin Easy 2.0 | Adjust Bottle Success Rate18 | 19 | |
| Robotic Manipulation | RoboTwin Hard 2.0 | Adjust Bottle Success Rate68 | 5 | |
| Robot Manipulation | LIBERO-PRO Spatial suite (test) | Orientation Score100 | 4 | |
| Robot Manipulation | LIBERO-PRO Goal suite (test) | Ori Success Rate100 | 4 | |
| Robot Manipulation | LIBERO-PRO Long suite (test) | Ori Success Rate99 | 4 | |
| Robot Manipulation | LIBERO-PRO Object suite (test) | Orientation Success100 | 4 | |
| Move tennis ball from yellow plate to blue plate | Real Robot | Success Rate97 | 2 | |
| Pick red cube into yellow plate | Real Robot | Success Rate74 | 2 |