Efficient Training of Diffusion Models with Token Routing (TREAD)
Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for…
Read the full articleYou might also wanna read
Google's DiffusionGemma achieves 4x faster text generation using diffusion-based approach
An overview of DiffusionGemma, an exceptionally fast text generation model with up to 4x faster speeds.
deepmind.google·1mo agoDiffusionGemma: The Developer Guide
DiffusionGemma is an experimental text-generation model built on the Gemma 4 architecture that uses diffusion-based parallel generation inst
Self-Routing: A Parameter-Free Approach to Expert Routing in Mixture-of-Experts Models
Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a lear
arxiv.org·8d ago
Three training-time interventions improve diffusion-based speculative decoding by 21-76%
Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs s
arxiv.org·22d agoOrbitQuant: Efficient Quantization for Diffusion Transformers
OrbitQuant is introduced, a method for post-training quantization of diffusion transformers without the need for calibration data. The techn
Google's DiffusionGemma open AI model offers 4x faster text generation but faces accuracy trade-offs
Diffusion AI is most common in image generation, but it can make text outputs much faster.
arstechnica.com·1mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.