#Distillation
3 articles with this tag
AI Research
Nvidia's Ziv Ilan on Faster Diffusion Models
Nvidia's Ziv Ilan explains how to reduce diffusion model latency using quantization, caching, and distillation, plus the new FastGen library.
3 days ago
Artificial Intelligence
Ben Kunkle on Building Zed's Zeta2 Prediction Model
Ben Kunkle from Zed Industries explains the architecture and data pipeline for building Zeta2, an AI model that predicts code edits.
20 days ago
AI Research
Cross-Architecture dLLM Distillation
TIDE framework enables cross-architecture distillation for diffusion large language models, achieving significant performance gains with smaller student models.
about 2 months ago