We have 3 of 26 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.
OASIS is proposed, an outlier- and sink-aware method that stabilizes dual-normalized attention-residual architectures through explicit null routing and token-to-depth null coupling and offers insight into the low-bit sensitivity observed in AttnResidual.
A unified view of progress reward modeling for robotic learning is provided in three connected steps that connect what a progress model is, how it is built, and how its quality is validated.
LLMZero, an agentic system that optimizes training trajectories via tree search by diagnosing pathologies at each checkpoint and proposing coordinated multi-parameter transitions, discovers strategies that improve over the base model and over grid search and over grid search, consistently outperforming random search an...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
