- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes E²PO, an energy-based preference optimization framework for concept erasure in text-to-video (T2V) models. The method introduces a multi-negative energy discrepancy objective to suppress undesirable generations and a Manifold-guided Target Anchoring (MTA) strategy to preserve unrelated spatial and temporal semantics. Experiments on nudity, identity, and object erasure demonstrate improved erasure effectiveness, adversarial robustness, and video generation quality compared with existing baselines.
Critical strengths
-
The problem is essential. The paper addresses the challenges of concept erasure in T2V models, where undesirable concepts are entangled with motion, temporal dynamics, and scene structure.
-
The method is well-motivated. Combining multi-negative preference optimization with semantic target anchoring provides a reasonable approach to balancing erasure effectiveness and preservation of generation capabilities.
-
The experimental results are convincing. E²PO consistently outperforms representative baselines across multiple erasure tasks. The extensive ablations, robustness evaluations, and additional analyses in the appendix further support the effectiveness of the proposed method.
Critical weaknesses
-
The clarity of methodological novelty is limited. Although E²PO is motivated by energy-based distribution shaping, its practical objective closely resembles existing multi-negative contrastive preference optimization. The unique contribution of the energy-based formulation remains insufficiently distinguished from conventional preference optimization.
-
The ablation study shows that the null target achieves stronger erasure effectiveness at the cost of slightly lower generation quality. Does this suggest that MTA primarily shifts the erasure–preservation trade-off rather than providing a substantive improvement? This raises questions about the necessity and unique contribution of MTA.
Questions for authors
-
Could the authors further clarify the essential methodological distinction between E²PO and conventional multi-negative contrastive preference optimization, particularly the unique benefits introduced by the energy-based formulation?
-
Could the authors further justify why semantic proximity in the text-conditioning space is a reliable criterion for preserving video motion and temporal structure?
-
Following 2, could the authors clarify whether MTA provides benefits beyond adjusting the erasure–preservation trade-off, particularly given the stronger erasure effectiveness achieved by the null target?
-
(Minor) About comparison with recent baselines. The evaluated baselines are primarily from 2024–2025. Could the authors briefly discuss the availability of more recent T2V concept erasure methods and clarify the rationale behind the selected baselines?
I am open to raising my score if the authors can adequately address these concerns during the rebuttal.