Poster · Sydney

Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference

Name: Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference
Start: 2026-12-10T10:00:00+11:00
End: 2026-12-10T13:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Thu 10 Dec 2026, 10:00–13:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 5
Authors: Zhichen Zeng, Xichong zhang, Junpan Wu, Yifei Zuo, Chi-Chih Chang, Jiayi Wang, Maohua Nie, Ji Liu, Ang Li, Banghua Zhu
Organisations: RadixArk, UW, University of Science and Technology of China, NVIDIA, Northwestern University, Cornell University, University of Washington, Meta
QRS classification: Attention and transformers, Language models, Generative models

Open in schedule Official page