- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes VIGOR, a Fisher-geometric model editing framework designed to mitigate Visual Blindness in Video-LLMs. The method introduces a structure-preserving Visual-Null intervention to identify editing gains that persist without informative video content. It then applies Fisher-orthogonal residualization to remove the blind editing component and derives a closed-form, minimum-information update. The authors also introduce Grounded Interaction Editability for principled layer selection. Experiments across four Video-LLMs on VMEB demonstrate strong editing performance, near-zero Visual-Null gains, and improved stability under sequential edits.
Critical strengths
The paper addresses Visual Blindness in Video-LLM editing, where successful editing may rely on text-side shortcuts rather than visual evidence. The Visual-Null intervention provides a useful way to distinguish editing success from video dependence.
The proposed Fisher-orthogonal residualization connects Visual-Null analysis to parameter updates. The minimum-information objective and Grounded Interaction Editability provide a coherent framework for editing direction and layer selection.
Experiments across four Video-LLMs demonstrate strong editing performance and near-zero Visual-Null gains. The ablation studies and sequential editing experiments further support the effectiveness of the proposed components.
Critical weaknesses
The paper motivates Fisher Geometry by arguing that Euclidean distance does not adequately reflect functional changes in model predictions. While the connection between Fisher Information and local KL divergence is well established, the paper does not sufficiently explain why Fisher Geometry is particularly suitable compared with other non-Euclidean metrics. The ablation study only compares Fisher Geometry with Euclidean geometry, leaving the benefits over alternative curvature-based metrics unclear.
Visual Blindness has already been investigated in Video-LLM editing, while orthogonal projection and Fisher-based layer selection have also been explored in existing model editing methods. Although combining these ideas for video-grounded editing is meaningful, the paper does not clearly establish which aspects of the proposed formulation represent fundamentally new contributions beyond existing approaches.
The relationship between Grounded Interaction Editability and minimum functional cost is derived under a local approximation. However, the paper does not directly establish how well the theoretical Fisher cost corresponds to actual changes in model predictions under finite or sequential updates. Additional analysis comparing the predicted cost with measured distributional changes would strengthen the theoretical claims.
Near-zero Visual-Null editing gains indicate reduced dependence on the blind pathway, but do not necessarily demonstrate that the edited model correctly utilizes the semantic or temporal information in videos. More controlled counterfactual evaluations would strengthen this claim.
Questions for authors
Why is Fisher Geometry particularly appropriate for video-grounded editing compared with other non-Euclidean or curvature-based metrics? Could the authors provide further theoretical justification or comparisons with alternative metrics?
Given existing work on Visual Blindness, orthogonal projection, and Fisher-based model editing, what is the most distinctive technical contribution of VIGOR? Could the authors clarify its differences from closely related approaches?
How closely does the theoretical minimum functional cost correlate with actual KL divergence between the original and edited models? Does this relationship remain consistent under sequential edits?
Does suppressing Visual-Null gains necessarily imply that the edited model relies on meaningful visual information? Could the authors evaluate semantically controlled counterfactual videos, such as changes in actions or temporal order, to further validate video-grounded editing?