- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper develops a control-theoretic formulation of the linear representation hypothesis for vision-language-action models. It distinguishes probing a current physical quantity from probing its future value under a candidate action trajectory, and defines state-conditioned linear steering through changes in the expected propagated quantity. Under uniform Chen–Fliess conditions, the paper constructs shared finite-dimensional state representations that approximately support action-conditioned linear probes for multiple quantities of interest. On the policy side, it introduces a signature exponential-family abstraction and shows that an exact probe induces an affine natural-parameter path along which the expected quantity changes monotonically. A planar control-affine example with an analytically constructed oracle representation and 671 candidate action chunks numerically verifies the probing identity and steering mechanism. The results concern a constructed idealized system rather than empirical validation on learned VLA representations.
Critical strengths
1. A useful formulation of the distinction between static representation probing and action-conditioned physical prediction.
The paper points out an important limitation of applying the standard static probing view directly to embodied policies: the physical quantity relevant to a decision may depend on both the current state and the candidate action trajectory. The action-conditioned measurement map and state-conditioned steering direction make this dependence explicit. I also found the distinction between decodability and intervention useful: a quantity being linearly readable from a representation does not by itself mean that editing the representation will influence that quantity through the downstream policy. This is a useful way to separate probing from steering.
2. The idealized construction is explicit and easy to inspect.
The existence argument is constructive. Appendix B.1 stacks truncated Lie-derivative coefficients for the selected quantities, and Appendix A gives a uniform truncation-error bound. Under the exact-probe and exponential-family assumptions, the steering analysis relates the response derivative to the variance of the propagated quantity. The numerical example also specifies the dynamics, representation transformation, candidate actions, and base measure, so the reported mean shifts and KL costs are relatively easy to check. The example is clearly presented as an oracle verification rather than as evidence from a learned policy.
Critical weaknesses
1. The existence result does not establish realizability through the observation interface used to define the VLA representation.
The setup defines the representation as an observation-based map, , so the model does not have direct access to the physical state. However, Theorem 4.2 constructs a state-dependent representation from Lie derivatives of the quantities of interest, without requiring these features to factor through the observation map . The theorem therefore gives a full-state feature construction, but it does not show that the same construction is realizable under the observation restriction used in the VLA formulation.
This matters independently of how the representation is learned. If two physical states produce the same observation but different propagated quantities under the same candidate action trajectory, any observation-based representation must give them the same probe prediction. The worst-case error is then at least half the difference between the two propagated quantities, regardless of representation dimension. The paper clearly presents the construction as an oracle representation, but the connection to the VLA setting still seems to require an observation-sufficiency assumption, a formulation based on observation histories, or a clearer separation between state-space existence and observation-realizable representations.
2. The probing-to-steering connection relies on an additional compatibility assumption between the representation and the policy.
Section 5 identifies the representation used for probing with the natural parameter of a signature exponential-family policy. This does not seem to follow from the existence result in Section 4 or from signature expressivity alone. In particular, representing an action distribution in signature coordinates does not imply that those coordinates depend affinely on the hidden representation being edited. Under the assumed parameterization and an exact probe, the intervention produces an exponential tilt by the propagated quantity, which is what gives the nonnegative-variance derivative.
The numerical example constructs both the exact probe and the compatible policy by design, so it does not test whether this compatibility holds for a learned representation and policy head. It is therefore still unclear how directly the steering result carries over to learned VLA models. I do not think a large-scale robot benchmark is necessary here, but either a compatibility result for an observation-conditioned policy or a small experiment on a learned representation and action head would make this connection much more convincing.
Questions for authors
1. Observation-based realizability.
Under what assumptions does the representation in Theorem 4.2 factor through the observation map , or through an observation history? The theorem constructs a full-state representation from Lie derivatives, while the original VLA formulation restricts the representation to observations. How should the result be interpreted when two physical states have the same observation but different propagated quantities under the same action trajectory?
2. Compatibility between learned activations and policy natural parameters.
What property of the action head would make its signature natural parameters affine in the representation being edited? This seems to be an additional assumption rather than something implied by signature expressivity. Is there a condition that could be checked for a learned policy, without replacing it with the oracle exponential-family policy?
3. Minimality and the dual-coordinate argument.
Appendix C.1 assumes a regular, minimal exponential family and uses the inverse relation between natural and expectation coordinates. However, the signature contains , and for a fixed horizon some pure-time coordinates are also constant across action paths. These directions should not change the normalized action distribution. How are they removed when defining the minimal exponential family used in the argument? I do not think this affects the variance-based monotonicity result, but it seems relevant to the strict-convexity and inverse-coordinate claims.
4 comments
(Part 2/2)
2. Representation–Policy Compatibility (W2, Q2)
We agree that directly identifying the representation with the natural parameter was restrictive in our original formulation. We have therefore generalized the signature exponential-family parameterization by introducing a differentiable mapping (Definitions 5.1–5.2), separating the learned VLA representation from the policy natural parameter. This is motivated by the universal approximation properties of path signatures, which allow continuous path functionals, including suitable policy log-density ratios, to be approximated through linear signature functionals. Theorem 5.3 preserves monotonicity along the natural-parameter path, while the new Corollary 5.4 provides a local steering direction in representation space.
Crucially, our experiments do not require the actual action heads to exactly satisfy the signature exponential-family assumption or explicitly identify . Instead, we work with the PCA-reduced representation and directly estimate the representation-to-expected-signature map . The steering direction is obtained by pulling back the probe direction through the action head:
This provides a practical connection between our theoretical steering principle and learned VLA action heads, without asserting exact exponential-family compatibility.
3. Additional Clarifications (W1, Q1, Q3)
Observation-based realizability. Our framework does not require reconstructing the entire physical state, but only retaining sufficient information about task-relevant QoIs and their action-conditioned evolution. For Theorem 4.2, a sufficient condition is that the relevant Lie-derivative coefficients factor through the observation map . Such dynamical information may also be available through sufficiently informative observation histories, as motivated by classical observability and delay-embedding theory. For example, a single image of a pendulum may reveal its angle, whereas consecutive observations can additionally reveal its direction of motion and angular velocity. We agree that observationally indistinguishable states with different propagated QoIs cannot admit an exact observation-based probe. Our new experiments provide empirical evidence that the required dynamical information is nevertheless accessible in the evaluated pretrained representations.
Minimality of the exponential family. We thank the reviewer for identifying this technical point. The empty-word and fixed-horizon pure-time signature coordinates are constant across action paths and therefore do not affect the normalized policy distribution. More generally, minimality requires restricting to identifiable parameter directions, or equivalently quotienting out all directions that contribute only action-independent constants. We clarify this restriction in the beginning of Appendix C.1. Importantly, the variance-based monotonicity result itself does not require minimality, since it follows directly from the exponential-tilting covariance identity.
We hope these substantially extended experiments and theoretical clarifications address the reviewer's main concerns and strengthen the connection between our framework and practical pretrained VLA models.
References
- Li, K., Patel, O., Viégas, F., Pfister, H., and Wattenberg, M. Inference-Time Intervention: Eliciting Truthful Answers from a Language Model. NeurIPS, 2023.
- Rimsky, N., Gabrieli, N., Schulz, J., Tong, M., Hubinger, E., and Turner, A. M. Steering Llama 2 via Contrastive Activation Addition. ACL, 2024.
Raise my score from 2 to 3
Thank you for the substantial revisions and additional experiments. The evaluations on OpenVLA-OFT and SmolVLA are particularly helpful and directly address my concern that the original results were demonstrated only through an oracle construction. I also appreciate the comparisons between static probe directions and directions that account for the learned action head, which make the distinction between decodability and effective intervention clearer.
The revised policy parameterization and the clarification of non-identifiable signature coordinates also address important parts of my theoretical questions.
My remaining reservations mainly concern the scope of the conclusions. The state-space existence result still requires an observation-sufficiency condition to connect it to the VLA observation interface, while the representation-space steering guarantee is local. The new experiments provide encouraging evidence in the evaluated setting, and I would encourage the authors to keep these distinctions explicit when relating the theoretical results to pretrained VLAs.
Overall, the additional experiments and theoretical clarifications substantially address my main concerns and strengthen the paper. Some reservations remain regarding observation-based realizability and the scope of the steering results, but the revisions have improved my assessment. I am therefore raising my score from 2 to 3.
We sincerely thank the reviewer for the careful reading of our revision and for raising the score.
We agree with both remaining points. Theorem 4.2 is an existence result in state space, and relating it to the VLA observation interface requires the observation-sufficiency condition discussed above; our probing results provide empirical evidence for the evaluated representations rather than a verification of that condition. We will keep these distinctions explicit when relating the theory to pretrained VLAs.
Thank you again for the constructive feedback, which has clearly improved the paper.
(Part 1/2)
We thank the reviewer for the thoughtful assessment of our work, particularly for recognizing the distinction between linear decodability and behavioral intervention. We have uploaded a substantially revised manuscript. The new Section 6 directly tests these predictions on pretrained VLAs.
1. Validation on Pretrained VLAs (W1–W2)
We particularly appreciate the reviewer's suggestion: "I do not think a large-scale robot benchmark is necessary here, but either a compatibility result for an observation-conditioned policy or a small experiment on a learned representation and action head would make this connection much more convincing."
We fully agree, and we have directly addressed this concern by extending our experiments to two pretrained VLA models, OpenVLA-OFT and SmolVLA. These models employ substantially different action-generation mechanisms: a deterministic MLP action head and a stochastic flow-matching action expert. Our revised Section 6 investigates whether the two central properties of our framework can be observed in their learned representations.
Action-conditioned linear probing (Figure 2, Table 4). Our signature-based linear probes predict the chunk-induced changes in physical QoIs with held-out R2=0.90–0.98 on OpenVLA-OFT and 0.79–0.96 on SmolVLA, outperforming conventional direct and additive probes. More importantly, even at matched parameter counts, nonlinear MLP readouts and unstructured MLPs improve the mean R2 by at most 0.005 on OpenVLA-OFT and 0.001 on SmolVLA, and widening them to 256 hidden units adds at most 0.008 and 0.007, respectively, providing empirical evidence for the proposed linear structure in learned VLA representations. Please see lines 385–389 for detailed descriptions of each method.
Probe-derived linear steering (Tables 1–2). We further demonstrate that this information can be used to modify the actual behavior of pretrained VLAs. By accounting for the action head through its Jacobian, our method produces monotonic responses in 138/140 held-out states on OpenVLA-OFT, with cosine similarity 0.98–1.00 to the simulator oracle gradient. On SmolVLA, it achieves monotonic responses in 83% of the 53 oracle-steerable states, with median cosine similarity 0.92.
Interestingly, these results directly support the reviewer's observation that decodability does not necessarily imply successful intervention. Conventional static probe directions often steer physical quantities in the wrong direction, whereas our action-conditioned, head-aware directions are much more successful at intervention. Furthermore, our closed-loop experiments demonstrate meaningful behavioral modification without additional fine-tuning or data collection (Section 6.3 and Figure 3). In a separate behavioral redirection experiment, representation steering successfully manipulates an alternative mug in 19/25 trials, whereas modifying the language instruction alone fails in 75/75 trials (three rewritten instructions). We further compare with fixed steering vectors from language models, CAA (Rimsky et al., 2024) and the ITI probe direction (Li et al., 2023), applied at the same site with the same step size. Built from the same information as ours, they succeed in at most 10/25 at their best strength, against 19/25 for ours; a CAA vector built from hand-labelled task phases reaches 16/25. Ours is also ahead of every baseline at α=32 and 40. This mirrors the reviewer's point: directions that encode the target but ignore the current state and action steer less reliably than our state- and action-dependent direction. For more details, please check our demonstration website (https://teal-smakager-b0c294.netlify.app) showcasing our new experimental results.
We believe these additions directly address the central limitation identified in the review: the proposed probing and steering mechanisms are no longer demonstrated only in a simulator oracle construction, but are empirically validated on pretrained VLA models.
(continued in the next comment)