2 papers indexed here
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.
CANOPY, a multi-fidelity tree bandit that learns where the smoothness prior is valid rather than assuming it globally, is introduced, a multi-fidelity tree bandit that consistently improves matched-budget performance.
This work learns affine transformations between the final hidden states of independent models and evaluates them across embedding classification, out-of-distribution detection, and autoregressive text generation, finding that success is governed by two factors: tokenizer overlap, which correlates strongly with generati...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
