We have 4 of 5 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.
It is shown that a widely used dataset's stated assumption of no intra-group annotator variability is false, and it is shown that an LLM judge tracks the crowd pool over the expert pool on all three models the authors test, including one from a different vendor.
This work prunes two recent open-weight MoE models from different families, and shows that perplexity, the metric much of the pruning literature leans on, can rate a broken model above an intact one; that a lightweight fine-tune recovers about half of what aggressive pruning loses; and that against quantizing the full...
This work studies 24 open-weight monitors spanning nine pretraining lineages and a 29x range of detection skill, and reports that across six attacker models the gain result holds in all six, the agreement and cancellation results in five of six.
This work separates three arms applied to the same failed candidate: blind whole-solution resampling, spectrum-based localization followed by suspect-span infilling followed by suspect-span infilling, and same-length infilling at a disjoint random code span.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
