27cc3576a6f149e95cf68afc3e25cd6c.zip -

Reviewers generally agreed that the method offers superior accuracy and efficiency across multiple tasks, supported by thorough ablation studies on design choices.

Reviewers from the research community have shared their direct impressions of the work: 27cc3576a6f149e95cf68afc3e25cd6c.zip

One reviewer pointed out that the methods ZIP was compared against (like BLACKVIP and BPTVLM) were from 2023, and suggested that more recent 2024 benchmarks should have been included for a fairer comparison. Reviewers generally agreed that the method offers superior

Reviewers highlighted that the paper's design choices, specifically "feature sharing," were well-motivated and helped the model stay expressive despite the simplifications. Critical Perspectives including detailed ablation studies.

It addresses the high query requirements of existing methods by reducing problem dimensionality and using "intrinsic-dimensional gradient clipping."

Because black-box prompt tuning is a niche field, some reviewers found it difficult to judge exactly how "new" the method was compared to the very latest unpublished research. Community Feedback

Reviewers pointed out that the soft prompt reparameterization design choices were thoroughly tested, including detailed ablation studies.