arXiv cs.AI· Qiangong Zhou, Jiafeng Liang, Yimin Dong, Yang He, Hongxiang Li·· 12 小时前AI 评分22
TTT in VLA 模型：探索用人类演示训练
TTT in VLA Models: Exploring Training with Human Demonstrations
AI 导读
研究将 Test-Time Training（TTT）集成进 InternVLA-A1 和 Pi0.5，通过配对演示与机器人轨迹训练，探索基于人类演示的动作生成。在当前规模下，加入 TTT 与配对数据训练并未带来一致的演示目标选择；更短序列、全轨迹梯度连通和对比正则也未明显提升对演示的响应。演示缩减为单帧线索时，真机执行仍偏好固定位置的杯子。
正文 · 原文
Abstract:Long-horizon robot tasks require retaining and using past information. We integrate Test-Time Training (TTT), which stores context in fast weights, into InternVLA-A1 and Pi0.5 to study action generation conditioned on human demonstrations through training on paired demonstrations and robot trajectories. We implement memory transfer between the two phases and truncated backpropagation, and examine training objectives, gradient coverage, and contrastive regularization across video, short-video, and single-frame cue tasks. In our experiments, adding TTT and training on paired data at the current scale did not lead to consistent target selection based on demonstrations. Under the tested settings, shorter sequences, full trajectory gradient connectivity, and contrastive regularization did not clearly improve responsiveness to demonstrations. When demonstrations were reduced to single-frame cues, real-robot execution still showed a preference for cups at fixed positions. We document the implementation, training configurations, and observations to support further inspection and replication.
| Comments: | 22 pages, 6 figures, a techreport form standard-robots company |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.32094 [cs.RO] |
| (or arXiv:2610.32094v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32094 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qiangong Zhou [view email]
[v1]
Fri, 23 Oct 2026 02:55:23 UTC (2,483 KB)
来源：arXiv cs.AI · arxiv.org