We have 5 of 152 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
ASK, a kernel-based steering method that learns from elicited pairwise judgments without accessing teacher embeddings or collecting new human similarity annotations, is introduced, a kernel-based steering method that learns from elicited pairwise judgments without accessing teacher embeddings or collecting new human si...
Across seven few-shot benchmarks and two CLIP backbones, low-rank prompts match or improve dense CoOp at far fewer parameters, with the clearest gains on low-shot base-to-new generalization.
This work proposes ZOMP (Zeroth-Order Multimodal Prompt tuning), a query-efficient, fully forward-only method that tunes deep prompts in both the vision and text branches of a frozen CLIP model using simultaneous perturbation stochastic approximation.
It is argued that reference-based similarity rewards a fluent, comprehensive critique style rather than the selectivity and specificity of human critique, and that reference-based similarity gives a misleading picture.
REALM is proposed, which jointly learns the model parameters and a scalar expertise value for each annotator, entirely unsupervised and requiring nothing beyond annotator identity, and extends to multiple tasks via a learned expertise matrix.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
