Search papers, labs, and topics across Lattice.
6
0
7
8
The sharpness of neural network solutions is fundamentally tied to class distribution, revealing critical insights for optimization and generalization in deep learning.
AngularMuown not only enhances optimization stability but also outperforms its predecessor in competitive benchmarks, redefining expectations for matrix-aware optimizers.
Fixed-point convergence enables adaptive computation in reasoning tasks, allowing models to efficiently tackle complex challenges without unnecessary resource expenditure.
Forget trial-and-error: this paper derives hyperparameter scaling laws for modern optimizers directly from convergence bounds, potentially automating and optimizing the hyperparameter tuning process.
By strategically guiding self-play with challenging real-world examples, GASP unlocks a 2.5% performance boost in coding LLMs and conquers previously unsolvable problems.
Forget scaling up: smarter state mixing in linear recurrent networks lets you match LSTMs and Mamba on sequence tasks, closing the expressivity gap without sacrificing efficiency.
