用结构化监督让小模型在机器人任务中达到大模型水平
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
- 用分层思维链蒸馏，把大模型的推理拆解为计划与思考模块
- 0.9B参数模型在多个任务上超越7B基线，最高领先15.9分
- 适合资源受限场景的机器人智能系统研发者
视觉-语言-动作（VLA）模型将自然语言指令转化为机器人动作序列，但当前在LIBERO-Plus鲁棒性基准上表现优异的系统多采用30亿至70亿参数的骨干网络，内存需求超出嵌入式机器人预算。本文提出CoTinyVLA，基于0.8B参数的Qwen3.5骨干构建0.9B参数的动作模型，通过结构化监督实现鲁棒性，而非扩大模型规模。三个核心组件分别针对问题的不同维度：每步输入16帧历史图像并加入文本相机标记与时间戳；从350亿参数教师模型中蒸馏出任务级“计划”与块级“思考”跨度，涵盖任务阶段、夹爪状态与下一子动作；以及通过改写增强将40条基础指令扩展至800种变体。在覆盖10,030个扰动任务、七个扰动维度的LIBERO-Plus测试中，CoTinyVLA在空间、物体、目标和长程任务上分别取得90.8%、87.3%、86.6%和80.7%成功率，全面领先最强7B基线4.7、2.8、15.9和3.0个百分点，所有差距置信区间均不包含零。性能提升集中在最困难的评测维度：在机器人初始状态扰动下，现有11个基线模型在任一任务上的最高得分不超过53.2%，而CoTinyVLA在目标任务上达到73.6%，远超最强基线的39.9%。消融实验表明三组件可按扰动轴独立贡献，且在相同图像预算下，两摄像头间帧分配方式自身就贡献8.6分。闭环推理峰值显存仅2.25 GiB，替换任务计划为无内容或矛盾内容会导致成功度下降40至45分，证明计划模块至关重要。结构化监督使0.9B骨干模型超越所有更大规模模型。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets. We present CoTinyVLA, a 0.9B-parameter action model on a Qwen3.5-0.8B backbone that obtains that robustness by structuring supervision instead of enlarging the model. Three components target different axes of the problem: dual-view temporal input of 16 history frames per step with textual camera and time markers; hierarchical chain-of-thought (CoT) distillation from a 35B teacher into an episode-level Plan and a chunk-level Think span over task phase, gripper state and next subaction; and paraphrase augmentation expanding 40 base commands into 800 variants. On LIBERO-Plus, spanning 10,030 perturbed tasks across seven perturbation dimensions, CoTinyVLA reaches 90.8% on Spatial, 87.3% on Object, 86.6% on Goal and 80.7% on Long, leading the strongest 7B baseline on all four suites by 4.7, 2.8, 15.9 and 3.0 points, with every margin interval excluding zero. The gains concentrate on the hardest axes of the benchmark: across the eleven published baselines none exceeds 53.2% on Robot Initial States in any suite, whereas CoTinyVLA reaches 73.6% on Goal against 39.9% for the strongest baseline. Ablations show the three components to be separable by perturbation axis, and at a matched image budget how frames are divided between the two cameras and across time accounts for 8.6 points on its own. Closed-loop inference peaks at 2.25 GiB of allocated GPU memory, and paired interventions show the episode Plan to be load-bearing: replacing it with an empty or contradictory span costs 40 to 45 points of success. Structured supervision thus lets a 0.9B backbone exceed all of them. Code: https://github.com/BrainJellyPie/CoTinyVLA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。