发表机构
University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过六种条件设置和鲁棒性测试，评估了0.8B混合模型在操作任务中几何条件化的效果，发现训练时几何对齐无可靠优势，并揭示了坐标不变性与物理泛化间的差距。
AI 中文摘要
我们研究了物理状态输入如何影响一个为操作任务适配的0.8B混合语言模型，该模型具有620万可训练参数。我们在三个LIBERO-Spatial任务上训练了六种条件设置，并在三个随机种子和540次留出回放（rollouts）上进行了评估。将循环衰减门控条件化于几何增量上，成功率达到28.9%，而训练时对这些增量进行打乱则达到36.7%，在没有显式物体/目标几何信息时则为24.4%。两种几何策略在评估时均接收正确的输入。使用相同增量的令牌适配器得分为27.8%；不同种子之间的差异各异，结果尚不确定。令牌时钟条件化得分为11.1%，其中一个种子未能收敛。在单独的鲁棒性测试中，仅使用状态的相对坐标策略在帧重标注下保持了7/10的成功率，而所有四种测试的视觉策略在物体位移5厘米后最多只能达到3/20的成功率。这些结果表明，在这种配方下，训练时的几何对齐没有可靠的优势，并展示了坐标不变性与物理布局泛化之间的差距。论文附带了情节记录、种子级分析和图形生成代码。
英文摘要
We study how physical-state inputs affect a 0.8B hybrid language model adapted for manipulation with 6.2M trainable parameters. Six conditions are trained on three LIBERO-Spatial tasks and evaluated over three seeds and 540 held-out rollouts. Conditioning recurrent decay gates on geometric increments yields 28.9% success, compared with 36.7% when those increments are shuffled during training and 24.4% without explicit object/goal geometry. Both geometry policies receive correct inputs at evaluation. A token adapter using the same increments scores 27.8%; differences vary across seeds and remain inconclusive. Token-clock conditioning scores 11.1%, including one seed that fails to converge. In separate robustness tests, a state-only relative-coordinate policy retains 7/10 success under frame relabeling, whereas all four tested visual policies fall to at most 3/20 after a 5 cm object displacement. These results show no reliable advantage from training-time geometric alignment under this recipe and illustrate the gap between coordinate invariance and physical-layout generalization. Episode records, seed-level analyses, and figure-generation code accompany the paper.
Comments7 pages, 3 figures. Includes ancillary data and analysis code
