3 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.
This work derives a bias-variance decomposition of the expected gap between the model's and target's collision probabilities, showing that SFT is not inherently biased toward mode collapse or its opposite, and shows that diversity miscalibration can arise from finite-sample error and shrink as SFT better approximates t...
Low-Rank Adaptation (LoRA) is an effective approach for adapting large pretrained models by learning low-rank weight updates. In practice, the LoRA rank is used to control an adapter's parameter budget and representational capacity. We show that this view is incomplete: while the nominal rank determines the representat...
It is demonstrated that even with multi-billion parameter models and extensive training, current Vision Language Models fall short in the seemingly simple task of tool detection in neurosurgery, and experiments suggest that current models could still face significant obstacles in surgical use cases.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
