Skip to content

Author

Kavitha Srinivas

We have 3 of 34 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.

BOReFT: Manifold Steering of Language Models for Black-box Optimization

BOReFT is introduced, which learns a compact, low-dimensional space of hidden-state interventions in a frozen language model, and uses this space as the search domain for Bayesian optimization with an external scoring function, and provides a principled new bridge between discrete proposal spaces of LLM-based search an...

Dhruv Agarwal, Rico Angell, Kavitha Srinivas et al. · 0 citations

Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks

TEmBed is introduced, the Tabular Embedding Test Bed, a unified benchmark for systematically evaluating tabular embeddings across four representation levels: cell, row, column, and table and shows that which model to use depends on the task and representation level.

Liane Vogel, Kavitha Srinivas, N. D'Souza et al. · 4 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.