Skip to content

Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies

Sep 2026 · 0 citations · 33 references
Computer Science

Abstract

Action-chunked visuomotor policies predict overlapping trajectories, so every executed action is covered by several predictions. Temporal ensembling smooths execution by combining these predictions with an exponentially weighted mean. One corrupted prediction can move the aggregate without bound: its breakdown point is 0. We use adversarial corruption to stress this deployed aggregator and to compare two kinds of guarantee. A metric guarantee bounds the response to a perturbation of a given size. A combinatorial guarantee instead bounds the damage when at most q of the M candidates covering a timestep are corrupted, whatever their size. Encoder adversarial fine-tuning recovers 44% of the loss under the published patch attack, but only 7.3% after the attacker's step size is increased. By contrast, the coordinate-wise median of the same candidate set keeps its recovered fraction flat as attack optimisation increases. Median temporal ensembling costs one line and requires no retraining. Across 25 (configuration, corruption-level) combinations it is never worse than the mean and is significantly better in 15. It also transfers to a second policy class, and it recovers performance under a failure with no attacker in the loop at all: camera frames that arrive blank. Its effect on clean data is configuration-dependent, from -0.04 to +0.07. We also give the boundary: corruption that shifts every covering prediction by the same amount is invisible to this whole family of statistics, and no equivariant aggregator can remove it.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Measuring the Stability Assumption Behind Action Chunking

Action chunking improves the performance of policies learned by behavioural cloning, and several mechanisms have been proposed to explain why, including temporal consistency, horizon reduction, representation learning, and reduced error compounding. We instead study what happens to an action error once it enters the sy...

Aryan Goyal · 0 citations
#artificial intelligence Preprint Oct 2026

PermVLA: Factorization Order as a Regularizer for VLA Learning

Vision-language-action (VLA) policies commonly learn action chunks through a fixed left-to-right (LTR) factorization, although the same expert trajectory distribution admits many valid chain-rule factorizations. We identify factorization order as an overlooked regularization choice and introduce causally anchored permu...

Yan-Qiao Chen, Yu-Han Rui, Dong-Sheng Hou et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Beyond Scalar IoU: Structured Verification from Rollout Groups for Video Temporal Grounding

This work introduces SUTURE, which conditions verification on the rollout group and exploits its structure at two complementary scales: disagreement across rollouts controls how strongly the target is reweighted, while coverage at each position determines where reward mass is redistributed.

Youngjae Cho, Won Young Jhoo, Jongsuk Kim · 0 citations
Preprint Oct 2026

LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts

Scaling expert demonstrations alone does not enable generalist robot policies to improve from deployment. Real-world rollouts contain successes, suboptimal behavior, and failures: imitating every recorded action can reinforce poor behavior, while filtering out failures discards evidence of physical interactions and the...

Wen-Xuan Guo, Ying-Ping Liang, Zhao-Guo Wang et al. · 0 citations
Preprint Oct 2026

MARS: Systematic Multi-Level Acceleration for World Action Models

World Action Models (WAMs) have emerged as a promising alternative for embodied intelligence by jointly predicting future world states and robot actions. However, their heavy visual encoding and iterative generative inference incur substantial latency, limiting their applicability to high-frequency closed-loop control....

Zeng-Yuan Zuo, Yong-Chang Zhang, Guang-Yu Zhao et al. · 0 citations
#diffusion models Preprint Sep 2026

JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction

JEPA Policy is introduced, a diffusion-free framework that uses the action chunk and its observed future representation as paired training targets as paired training targets and supports paired future-representation supervision supervision as a practical approach to low-latency visuomotor imitation without iterative ge...

Jie Xu, Kang-Jin Yu, Zi-Yi Jin et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.