We have 5 of 27 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.
The two studies show that closed-loop GPU fine-tuning does not guarantee monotonic mobile gains, especially on harder classification tasks, and that multi-dataset, on-device measurement is needed to stress-test deployment objectives.
Direct-copy and negative-control analyses show that gains depend on source-target compatibility and LLM adaptation; stored source accuracy alone does not predict transferability.
Large language models (LLMs) can generate neural-network modifications, but unrestricted generation is often invalid or harmful. This paper studies a narrower setting: improving a weak target model using a stronger same-family source model from a neural-network database. We propose a source-guided candidate-generation...
A cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum warmup yields 27% peak SR at substantially lower accuracy than the CIFAR-10 equivalent, is reported, consistent with the increased synthesis difficulty of the unq-family anchor architecture.
This dataset defines a new basis for reproducible and data-driven AI design, advancing the emerging paradigm of LLM-driven AutoML and architectural generalization across modalities and hardware.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
