ASRD: Revolutionizing Decoding with Anchor Tokens
Diffusion Large Language Models face challenges in balancing speed and quality. The new ASRD framework promises significant improvements without additional training.
Read the full articleYou might also wanna read
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·20d ago
Fast-dLLM: Training-Free Acceleration Method for Diffusion Language Models Using KV Cache and Parallel Decoding
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capa
arxiv.org·8mo ago
Speculative Speculative Decoding: Parallelizing LLM Inference for Faster Performance
Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by
arxiv.org·4mo ago
LK Losses: A New Training Objective to Optimize Acceptance Rate in Speculative Decoding for LLMs
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate
arxiv.org·1mo ago
iLLaDA: An 8B Masked Diffusion Language Model Trained with Bidirectional Attention
Modern large language models are predominantly trained with autoregressive factorization and causal attention. We present \emph{iLLaDA}, an
arxiv.org·20d ago
Beyond Autoregression: LLaDA2.1 and the Case for Self-Editing Language Models
Introduction Every mainstream large language model today generates text the same way: one token at a time, left to right, no looking back. I
Comments
Sign in to join the conversation.
No comments yet. Be the first.