We have 3 of 34 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.
Diffusion models are typically viewed as stochastic processes that transform noise into data. We take a complementary perspective: a diffusion model defines a family of deterministic dynamical systems indexed by noise scale. At each fixed scale $\sigma$, we treat the denoiser as a self-map and study its dynamics. For a...
This work introduces SACReg, a spectral anti-collapse regularizer motivated by an analysis of $\lambda$-balance, which captures the relative scale of weight matrices across layers, and proposes $\lambda$-JEPA, which improves over LeJEPA and VISReg on ImageNet-1k classification and in average linear-probe transfer perfo...
ADAPT---Amortized Distillation Across Post-Trained LLMs is introduced, a framework for amortizing distillation across both axes of a model family: size and post-training variant, producing models for interpolated sizes across post-trained variants with a single distillation run.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
