4 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.
Evaluating claim admission in shared agent memory is challenging because repeated claims may be mistaken for independent evidence. An agent may copy or paraphrase a retrieved belief, while admitting a false claim exposes subsequent agents to it. To study this problem, we introduce the Correlated Promotion Benchmark (CP...
It is shown that on MATH-500 the rate dependence does not reproduce under LoRA, scoping that result, while the ~10 pp cost of selective training does, and reported the arm x rate matrix, not a shared-rate column, as a precondition for selector comparisons.
This work takes the most direct such measure, the exact layerwise activation cross-term of a factorial ledger, establishes its causal anatomy, and asks what it tracks, and takes the most direct measure, the exact layerwise activation cross-term of a factorial ledger, and asks what it tracks.
Weight-space composition supports coarse, input- and format-conditioned functional statements -- not a universal merging-performance predictor, and not one that training-format evaluations can see.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
