Tag: diffusion language models
Browse our exclusive articles!
DepCap: Fast Adaptive Block-Wise Decoding for Diffusion LMs
DepCap enhances diffusion language model inference with adaptive block-wise decoding, boosting speed up to 5.63x while maintaining high-quality output.
Saber: Fast, High-Quality Sampling for Diffusion Language Models
Discover Saber, a training-free sampling method boosting speed and accuracy in diffusion language models for efficient code generation.
Diffusion Language Models Boost Speech Recognition Accuracy
Explore how diffusion language models enhance speech recognition with bidirectional context and joint-decoding for improved ASR accuracy.
Introspective Diffusion Language Models: High-Quality NLP
Discover Introspective Diffusion Language Models (I-DLM) that combine diffusion and autoregressive strengths for superior NLP quality and efficiency.
Exploiting Denoising Flaws in Diffusion Language Models
Discover how denoising irreversibility exposes vulnerabilities in diffusion language models and explore strategies to enhance AI safety and robustness.