3rd Workshop on Efficient and On-Device Generation (EDGE)

Accepted papers (15)

Fetched from OpenReview (v2) on 2026-06-10.

1. ☆A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM–Transformer Models

   Jason Kong, Nilesh Prasad Pandey, Flavio Ponzina, Tajana Rosing · PDF

2. ☆A Spike-Gated Residual Unit for Information Flow Control in Transformers

   Kiran Nair, Rodrigue Rizk, KC Santosh · PDF

3. ☆BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models

   Fei Deng, yanwu xu, Zhipeng Bao, Zhixing Zhang, Haolin Jia, Karthik Raveendran, Jianing Wei · PDF

4. ☆CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers

   Zhuojin Li, Hsin-Pai Cheng, Hong Cai, Shizhong Han, Fatih Porikli · PDF

5. ☆DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

   Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde · PDF

6. ☆Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference

   Yifu Ding, Xinhao Zhang · PDF

7. ☆DirectFlow: One-Step Posterior Transport Distillation for Blind Face Restoration

   Eashan Adhikarla, Brian D. Davison · PDF

8. ☆EdgeDiffusion: Latency-Optimized Diffusion Models for Real-Time On-Device Visual Anonymization

   Zihao Han, Xueyan Gong, Fengyi Wu, Yifei Dong, Jingqi Xu, Jingdong Sun, Feng Liu, Siyu Huang, Zhi-Qi Cheng · PDF

9. ☆ELT: Elastic Looped Transformers for Visual Generation

   Sahil Goyal, Swayam Agrawal, Gautham Govind Anil, Sujoy Paul, Aditya Kusupati, Prateek Jain · PDF

10. ☆Energy-Adaptive Diffusion via Dynamic Token Pruning for Carbon-Efficient On-Device Generation

    Mahule Roy, Subhas Roy · PDF

11. ☆HLA: Hadamard Linear Attention

    Hanno Ackermann, Hong Cai, Mohsen Ghafoorian, Amir Habibian · PDF

12. ☆ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction

    Mustafa Munir, Harsh Goel, Xiwen Wei, Minkyu Choi, Sahil Shah, Kartikeya Bhardwaj, Paul N. Whatmough, Sandeep P. Chinchali, Radu Marculescu · PDF

13. ☆On the Limits of Token Reduction for Efficient Unified Vision Language Training

    Siyi Chen, Weiming Zhuang, Jingtao Li, Lingjuan Lyu · PDF

14. ☆Token-Aligned Hierarchies for Lightweight Super-Resolution

    Jinendra Malekar, Lingjia Shi, Peyton Chandarana, Ramtin Zand · PDF

15. ☆Training-Free Layout-to-Image Generation with Marginal Attention Constraints

    Huancheng Chen, Jingtao Li, Weiming Zhuang, Haris Vikalo, Lingjuan Lyu · PDF