We have 3 of 7 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.
DropVLA is presented, an action-level backdoor attack that forces a reusable action primitive to execute at attacker-chosen decision points under a realistic pipeline-black-box setting with limited data-poisoning access, using a window-consistent relabeling scheme for chunked fine-tuning.
The results suggest that directly asking for the target response may not always yield the most effective score for predicting it, and that comparing direct scores with indirect paths through related judgments may reveal a more effective predictive route.
Interaction can reduce the required number of tests by a quadratic factor, but the apparent exponential branching of an interactive evaluation does not yield an exponential query advantage.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
