- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
PACO works on video detoxification that removes harmful contents in a video with a frozen instruction-based video editor. For each video, an MLLM proposes 25 atomic edit instructions. Their CFG directions form a dictionary, and the editor is steered by a sparse linear combination of these directions. The coefficients are optimized per video with an evolution strategy. It also provides PACO-2K benchmark, consisting of 2,450 videos across 14 safety categories.
Critical strengths
- Detoxifying videos by editing, rather than filtering them out, preserves the amount of usable data, since harmful videos can be retained in a safe form instead of being discarded.
- The method is training-free and editor-agnostic, and the learned sparse coefficients are easy to inspect.
Critical weaknesses
- The problem formulation is crude with an unjustified assumption, and the method has very limited novelty. PACO assumes that summing the CFG directions of independently proposed instructions realizes the union of their edits, but this is supported only by analogy and never tested. The velocity field is nonlinear in the condition, and additive composition requires independent concepts, whereas detox atoms typically target the same region and interfere. Moreover, up to 25 directions, with coefficients as large as 15, are applied uniformly over space and time without any specific design or analysis. The paper's own non-optimized compositions (SEGA; MLLM-predicted coefficients) barely improve over plain CFG, so the coefficients act as a knob for black-box search rather than as interpretable edit strengths. Semantic harms such as misinformation or hate also fall outside the formulation. Finally, combining velocity fields under multiple conditions is well established, and a plain linear combination offers no novelty.
- Prohibitive cost and circular evaluation. Each video requires hundreds of full editor runs, each with 25+ guidance passes per step, which is several orders of magnitude more compute than a single edit, yet no runtime is reported. Moreover, the comparison is unfair. PACO directly optimizes the same judges used for most reported metrics, while all baselines are single-shot without judge feedback.
Questions for authors
- A detailed time statistics of the whole inference pipeline.
- How often does the 25-atom dictionary contain no edit that targets the toxic content?
- Can you provide evidence that CFG directions of different atomic edits compose additively in the editor's velocity field? For example, does applying two atoms jointly reproduce the effects of applying each one alone, especially when they target the same region or use large coefficients? If composition is not additive, in what sense are the optimized coefficients interpretable edit strengths, rather than parameters of a black-box search?