- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The authors identify an important issue: Vision-language models frequently encounter challenges in explaining which visual cues drive their spatial reasoning capabilities.
And devise an interesting method to address it: Utility Probe (U-probe), a training-free approach that identifies answer-conditioned feature subspaces they call Utility Space (U-Space). By linking token representations with answer gradients, this technique establishes the causal roles of specific visual elements without requiring model retraining.
They then ran comprehensive experiments to demonstrate that scene-level spatial tasks depend heavily on scene structure, such as foundational elements like walls and floors, rather than solely relying on the primary objects mentioned in prompts. Furthermore, they show that tracking regional utility early in the supervised fine-tuning process serves as an effective diagnostic tool to predict final model performance.
Critical strengths
Reading this paper, 2 things stand out for me.
-
It helps bring to light a classic “AI interpretability issue”: proving causality rather than correlation. While I have seen papers that show where a model looks (a lot of them), this paper focuses on “why it answered the way it did”. That is, I think Utility Probe (U-probe) is very interesting.
-
It presents a practical "early warning system" for training expensive models: knowing early on whether a training run is going to succeed or fail could be a huge practical advantage. The authors discovered that by measuring how much "utility" a model retains on key background elements (like walls and floors) after just 20 training steps, they can predict how well that model will perform on spatial benchmarks hundreds of steps later.
Critical weaknesses
Reproducibility.
I appreciate that the authors include details about the models and experiments; however, my primary benchmark for reproducibility is an inspectable anonymous codebase. I believe the diagnosis is complex enough that minor implementation choices in gradient hooking, tensor normalization, or token boundary assignment can alter the results. While I may not necessarily run the code, submitting it now will make it easier for the authors to publish it later so others can use it.
Questions for authors
-
In Figure 3, all the extreme-projection patches look to me like nondescript crops of plain wall texture. Beyond manual inspection, how did the authors quantitatively confirm that these top U-Space axes reflect meaningful 3D geometry rather than visual noise or high-norm background tokens?
-
U-probe relies on a first-order linear approximation (coupling hidden token states with first-order answer score gradients). How well does this linear framework capture multi-step, non-linear spatial reasoning across 64 video frames? Have the authors tested whether higher-order gradient interactions or non-linear probes reveal different feature subspaces?
-
Since U-probe pools tokens across all 64 frames and erases temporal sequence, isn't a frame-agnostic linear probe mismatched for diagnosing sequential spatial reasoning?
-
Any insights on how one could convert U-Space into a performance booster?
3 comments
Thanks to the authors for the detailed response and for providing the code. I appreciate the extra effort with the depth decoder in Appendix K.4 and the token-norm checks.
That said, I have to admit I'm a bit disappointed that several concerns are not directly engaged:
-
Figure 3 remains uninterpretable: If proving that these extreme tokens carry 3D geometry requires training an external 3-layer conv decoder on a rank-64 subspace in the appendix, then Figure 3 itself doesn't demonstrate this to a human reader. I would like to see the intuition and understand the figure.
-
Temporal collapse and linear assumptions: Re-running the non-linear model to show that perturbing features changes logits only confirms causality. It doesn't show that a first-order linear probe models multi-step reasoning. More importantly, simply noting that the VLM's inputs are sequential doesn't change the fact that U-probe pools all 4,096 tokens across 64 frames into a single static average. It remains frame-agnostic, which sidesteps how dynamic, sequential video reasoning actually unfolds over time.
-
Actionability and "Future Work": Deferring non-linear probes, frame-aware formulations, and performance-boosting mechanisms to future work confirms that U-Space currently functions as a post-hoc diagnostic rather than an actionable tool for model improvement.
Overall, the paper presents an interesting diagnostic, but the methodological mismatch for sequential video tasks and the heavy reliance on "future work" for key limitations leave me on the fence.
Thank you for your follow-up and for acknowledging the code release and additional analyses. We now address your questions below.
- The interpretability results
We have revised Figure 3 to show full-frame examples for two question types: counting and room size. We select patches with large positive and negative projections onto the leading U-Space axis. The same three frames are shown for both question types, comparing their visual patterns directly. Positive (P) and negative (N) projections are displayed together within each frame. We choose the same frame across different question types to make the task dependence visible and the visual concept more interpretable in the scene context. "Counting" highlights object-related regions, including object groups, water-tap, and chair parts, in contrast to relatively uniform regions. "Room size" emphasizes extended surfaces and their boundaries or corners. These visual patterns provide qualitative interpretations related to object quantity and spatial extent, illustrating how the features associated with the leading axes depend on the question type. Full patch visualizations across models and question types as well as logit lens interpretation of the language-side U-space axis results are retained in Appendix E. The rank-64 depth decoder in Appendix K.4 provides separate evidence of recoverable depth information and is not required to interpret the visual contrasts in Figure 3.
- Linear approximation and temporal reasoning.
We appreciate the opportunity to clarify the scope of U-probe. Our goal of using U-probe is to understand what features are used by the VLMs to answer spatial questions, while it does not attempt to reconstruct the complete reasoning algorithm. It does not train a linear probe for the reasoning steps or predefined spatial variables. Its first-order objective identifies intervention directions, whose actual effects are evaluated through the full nonlinear VLM.
We agree that the aggregate matrix does not explicitly reconstruct temporal interactions or individual reasoning steps. The aggregation constructs a shared feature basis from token representations and answer gradients computed on the ordered video. Token-level utility remains associated with each token’s spatial position and frame. Such information is utilized by U-probe in temporal-sensitive spatial reasoning, e.g. the "appearance order" questions, to identify causal features for answering those questions in VLMs.
- Actionability
We agree that U-probe is not yet an actionable tool for model improvement. We use U-probe to identify and interpret the features used by VLMs in spatial reasoning, to diagnose and analyze the spatial SFT of VLMs, and to build an early warning system for the costly training. As Appendix J explains, an informative ranking across models does not imply that increasing the same utility fraction within one model will improve its accuracy.
We appreciate your positive assessment of U-probe's causal analysis and its application as an early training diagnostic. Thank you for highlighting reproducibility and the interpretation of our findings. We now address your questions below.
Thank you for your suggestion. We have submitted an anonymous codebase that could reproduce U-probe, SFT, and predictor analysis on all the models involved in our paper, in Supplementary Material. We will also release the trained model checkpoints to ensure a full reproduction of our work.
We clarify that we do not assume any pre-defined semantics of the token projection on the U-space axes. We first quantitatively confirm that the U-space axes carry answer-relevant features in Section 3, that they can alter the answer logit and steer the generated answer. Moving the token features along noise (e.g., random directions) does not give the same effect, as shown in Figure 2. We then interpret what are the semantics of the U-space features in the visualizations and logit lens. The extreme-projection patches do not come from a pre-defined semantics that they carry geometry information, but from the fact that they carry much answer-relevant features through U-space.
To investigate the relationship between the U-space projection and the token norm, we compute the Spearman correlation ρ between a token's projection onto the top U-space axis and its norm, over all image tokens. We choose 10 samples from each question type in VSI-Bench. The correlation is weak (∣ρ∣ median is 0.12 for signed projection value; ∣ρ∣ median is 0.07 for the magnitude; all results are on 5 VLMs), suggesting that the U-space projection is not choosing high-norm tokens.
To further investigate whether the U-space-projected token features carry geometry information, we decode the depth at that patch position. We use Depth-Anything-V2 to estimate the depth and build a small 3-layer convolutional decoder on the tokens, after projecting them onto the rank-64 U-space. The results are added to Appendix K.4 in the revised paper and show that those tokens carry local scene geometry through U-space.
We agree that U-probe uses a first-order linear approximation, and that spatial reasoning requires a multi-step and non-linear procedure. We therefore evaluate U-space interventions by rerunning the non-linear model after feature perturbations, and Figure 2 shows answer score changes and generated answer effects beyond the matched controls. These results validate the selected features' causal effect rather than relying on the approximation alone. We agree that higher-order gradients or non-linear probe of the answer can reveal complementary features, and we leave investigating them as future work.
We agree that pooling across all 64 frames does not retain an explicit frame index. However, it aggregates features and answer gradients computed from the ordered video. These quantities can contain temporal and cross-frame context. Reordering the input frames and recomputing the model can change the features, gradients and resulting U-Space. Thus, the aggregation need not be invariant to input frame order. The "appearance order" interpretations and regional deletion results provide evidence that the method can identify relevant features on a sequential task. We thank you for your suggestion and agree that a frame-aware method might further enhance the capability of U-probe. We plan to investigate it in the future work.
We believe that U-space could shed light on how to improve VLM performance, and discuss this possibility in pretraining and architectural design. U-space could inform the pretraining to build scene understanding by paying attention to scene structure regions, or motivate new VLM architectures that explicitly perceive the scene structure along with the object-centric representations. We provide a short discussion in Section 5 and Appendices I-J in the submitted paper on this topic, and we plan to investigate them in the future work.