GitHub·Code

juchengshen/CadLLM

Official PyTorch implementation of our Findings of ACL 2026 paper, "Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration"

3 stars·Updated Apr 2026
Open on GitHub

Authors

Repository owner

Linked papers

Code

Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration

arxiv · 2026

Why Lacuna links this resource
Repository names this paper

# Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration This repository provides the **official PyTorch implementation** of our paper: > **"Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration"** > *Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu* > Findings of ACL 2026 | [OpenReview](https://openreview.net/forum?id

README:focal_exact_title·Open evidence