- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes STAR, a training-free inference method for vision-language-action models. Motivated by a decline in the sensitivity of late-layer action representations to target-object masking, STAR applies an exponential moving average to residual updates across the final third of Transformer layers. The mixing coefficient is dynamically determined from recent proprioceptive signals, including directional continuity, translation magnitude, translational change, and orientation change. Experiments on three VLA backbones across four model–benchmark configurations report an average success-rate improvement.
Critical strengths
-
The method is lightweight and practically motivated. STAR modifies inference without updating model parameters or requiring additional full-model forward passes. Improving existing policies with limited computational overhead is a useful direction, and the reported real-robot latency overhead is modest.
-
The evaluation covers multiple model architectures. Improvements are reported for GR00T-N1.5, OpenVLA, and π₀.₅ across SimplerEnv and LIBERO-PRO. This provides broader evidence of applicability than evaluation on a single backbone.
-
The paper includes useful ablations and diagnostic controls. The experiments examine individual proprioceptive cues, fixed versus dynamic coefficients, and intervention depth. The masking analysis includes same-area background and random-pixel controls, while gradient-based analysis examines the sensitivity of the final actions rather than relying solely on attention visualization.
Critical weaknesses
-
DAMO already uses the same basic EMA residual-update rule to preserve information across layers and includes adaptive activation refinement and coefficient adjustment. STAR’s main methodological distinction therefore appears to be its proprioception-conditioned coefficient schedule and its application to robotic control. However, the main comparison is against DTP, which intervenes through visual-token pruning rather than residual momentum.
-
The object-awareness score measures the relative change in hidden states after masking the target object. A decrease in this score across depth does not necessarily imply loss of task-relevant information: it could also reflect changes in representation scale or transformations toward action-relevant features. Figure 1(c) also shows higher awareness at some intermediate layers than at the final layer used for action prediction, raising the question of whether the subsequent decline reflects harmful information loss or useful transformation toward action outputs.
-
Why should rapid motion changes or fine adjustments require weaker cross-layer EMA, while steady motion warrants stronger mixing? These phases may also require more accurate visual grounding. I think the ablations support the overall design but do not directly validate this directional assumption.
-
STAR motivates intervention through declining late-layer object awareness but fixes ρ = 2/3 without explaining how to identify the appropriate mixing region for a new model or deployment setting. The limited start-layer ablation does not establish such a procedure. I think the key problem of this paper might be: how to find a \rho for different dataset, or even different observation. I think \rho is variable.
Questions for authors
See weakness