Fast-dLLM v2: Efficient Block-Diffusion LLM
Paper • 2509.26328 • Published • 58
dLLMs
-
-
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 42 -
Attention Sinks in Diffusion Language Models
Paper • 2510.15731 • Published • 50 -
Diffusion Language Models are Super Data Learners
Paper • 2511.03276 • Published • 132 -
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
Paper • 2512.06776 • Published • 26 -
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Paper • 2512.13586 • Published • 93 -
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
Paper • 2512.14067 • Published • 16 -
DEER: Draft with Diffusion, Verify with Autoregressive Models
Paper • 2512.15176 • Published • 45 -
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
Paper • 2512.15745 • Published • 88 -
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
Paper • 2512.16229 • Published • 16 -
LLaDA2.1: Speeding Up Text Diffusion via Token Editing
Paper • 2602.08676 • Published • 72 -
DFlash: Block Diffusion for Flash Speculative Decoding
Paper • 2602.06036 • Published • 79 -
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 239 -
DMax: Aggressive Parallel Decoding for dLLMs
Paper • 2604.08302 • Published • 51