- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper challenges the assumption that steering functions are reversible and tests this assumption on MusicGen. The findings are that steering can remove a style but is unable to add it, quantifying this gap as a hysteresis loop. The authors argue this happens because a style is not a full-rank volume of the latent space, but instead a subset of it, composed of many thin real trajectories, so thin that it is impossible to land on them. From this result, the authors propose a “transport then project” technique, where at a fixed layer the hidden state is transported to a target class, and then replaced by the nearest trajectory in that class, which then continues with generation. This method reaches the target style on electronic music at both small and medium MusicGen sizes, and partly on jazz.
Critical strengths
- The transplant experiment shows that somewhere exists a clear threshold from which a target style can be reached from raw mixing, and furthermore it shows that many of the dimensions are needed for that to succeed.
Critical weaknesses
- I think what the authors propose can't be called steering. The hidden state at the selected layer is overwritten with the closest state in the transported class, for each step onward. In this way one track is being effectively replaced by another. The paper does acknowledge that none of the methods proposed preserve the source and that the similarity between outputs and the bank of clips was not measured. Listening to the demo leads me to this conclusion: the outputs are indeed nicer than the affine ones by a long margin, but they have little to do with the original tracks.
- The experiments are too narrow for the given claims. The title and abstract make general claims about steering functions and styles, but everything is tested on a single model family, over a single layer of a model, and on three attributes, with only automatic listeners. Tests on other models, for example a diffusion based one (such as Stable Audio Open), would be necessary to support any claim of generalizability.
- Lemma 2 doesn’t work. Taken literally it means that any change leaves a class and none can reach one. Furthermore, the -tube version of the argument undoes its first half, as in that manner less than pushes will stay inside the tube, so leaving is no longer a certainty. Finally, the empirical proof that classes/styles live in a thin set does survive (as hard NN beats soft 8-NN), but the proof that they are measure zero is little, as the alpha=0.5 mixing reaches ~70% for target classes.
Questions for authors
- Can the authors provide the original clips used for the bank? Or at the very least provide similarity metrics (perceptual ones) such as CLAP or MERT, between the bank and the outputs?
- Do the findings hold on other music generation models?
- Can the authors provide results from other layers and other attributes?
Thank you for the additional experiments which address several of my concerns. However, I remain concerned about whether the proposed method achieves genuine style editing rather than retrieval-based trajectory replacement, particularly given the limited evidence of source-content preservation. The broader theoretical claims may also require further validation. So I keep my score in rejection.