27cc3576a6f149e95cf68afc3e25cd6c.zip 【Recent】

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.

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a niche field, some reviewers found it difficult to judge exactly how "new" the method was compared to the very latest unpublished research.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 27cc3576a6f149e95cf68afc3e25cd6c.zip

It looks like there's no response available for this search. Try asking something else. One reviewer pointed out that the methods ZIP

The primary consensus among reviewers is that ZIP significantly reduces the "query cost"—the number of times you have to ask the model for a result—while maintaining or improving accuracy. Try asking something else

While the reviews were generally positive, experts noted a few areas for improvement:

This paper introduces a method called designed to improve how we tune large "black-box" models (like CLIP) when we don't have access to their internal code or gradients. Performance and Efficiency