arXiv：cs.AI· Yujin Wang, Junli Chen, Yixuan Li, Shunan Dong, Huazhong Yang, Yongpan Liu, Hongyang Jia·· 17 小时前
The Speedup Paradox：重新思考具身任务中的推理速度-质量权衡
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
AI 导读
研究提出 TISED 框架，统一分析量化、剪枝、异步推理等有损高效推理技术对具身任务的影响。结果显示，静态任务中优化虽降低单块耗时却可能拉长端到端任务完成时间；动态任务中适度的有损轻量化优化甚至可将任务成功率提升至基线之上，且两种效应的单调性与最优区间会随硬件配置变化。
正文
Abstract:Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as quantization, pruning, and asynchronous inference, accepting small action quality degradation in exchange for lower per-inference computation cost and inter-action latency. However, unlike traditional static ML tasks, embodied tasks involve repeated interaction with the environment, and task-level performance is determined not only by inference cost, but also by closed-loop effects unique to embodied execution, which remain insufficiently characterized in current efficient-inference studies. In this work, we propose TISED (\underline{T}ask-level \underline{I}nference \underline{S}peedup \underline{E}ffect \underline{D}ecomposition), an analytical framework that unifies diverse lossy lightweighting inference optimization techniques and decomposes their effects on static and dynamic tasks; using it, we uncover several paradoxical effects: (1) on \textit{static tasks}, optimization can sometimes lengthen end-to-end per-task completion time even as per-chunk time drops; (2) on \textit{dynamic tasks}, moderate lossy lightweighting optimization can raise task success rate even above the baseline; and (3) the monotonicity and sweet-spot location of both effects can shift with hardware configuration. Together, our findings provide a new perspective on adapting inference optimization techniques to embodied tasks. Source code: this https URL.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2606.28529 [cs.RO] |
| (or arXiv:2606.28529v3 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2606.28529 arXiv-issued DOI via DataCite |
Submission history
From: Yujin Wang [view email]
[v1]
Fri, 26 Jun 2026 18:28:52 UTC (3,034 KB)
[v2]
Tue, 30 Jun 2026 06:26:23 UTC (3,034 KB)
[v3]
Sun, 11 Oct 2026 03:54:43 UTC (3,192 KB)
来源：arXiv：cs.AI · arxiv.org