Daehoon Gwak

KAIST AI

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Inference & Quantization (1)Natural Language Processing (1)Training Efficiency & Optimization (1)

Frequent co-authors

Minhyung Lee (1)Junwoo Park (1)Jaegul Choo (1)

Papers (1)

Jul 14, 2026

Jul 14, 2026·also Affiliation:

Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques

Disentangling the intricate factors affecting inference speed reveals that effective acceleration of dLLMs hinges on specialized techniques rather than mere parallel generation.

Daehoon Gwak, Minhyung Lee, Junwoo Park +1

Inference & Quantization Natural Language Processing Training Efficiency & Optimization

Search

Daehoon Gwak

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)