activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Variance Reduction for Expectations with Diffusion Teachers

Jesse Bettencourt, Xindi Wu, Matan Atzmon +2

Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pi…

cs.LG2024

Multi-student Diffusion Distillation for Better One-step Generators

Yanke Song, Jonathan Lorraine, Weili Nie +2

Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep inference procedure. To overcome this, diffusion distillation techniques produce student…

cs.LG2024

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Zhengyi Wang, Jonathan Lorraine, Yikai Wang +4

This work explores expanding the capabilities of large language models (LLMs) pretrained on text to generate 3D meshes within a unified model. This offers key advantages of (1) lev…

cs.LG2024

Using Large Language Models for Hyperparameter Optimization

Michael R. Zhang, Nishkrit Desai, Juhan Bae +2

This paper explores the use of foundational large language models (LLMs) in hyperparameter optimization (HPO). Hyperparameters are critical in determining the effectiveness of mach…

cs.LG2024

JacNet: Learning Functions with Structured Jacobians

Jonathan Lorraine, Safwan Hossain

Neural networks are trained to learn an approximate mapping from an input domain to a target domain. Incorporating prior knowledge about true mappings is critical to learning a use…

cs.LG2024

Scalable Nested Optimization for Deep Learning

Jonathan Lorraine

Gradient-based optimization has been critical to the success of machine learning, updating a single set of parameters to minimize a single loss. A growing number of applications re…