Byunggwan Son — accepted AI-conference papers

2026

Relational Feature Caching for Accelerating Diffusion Transformers

Byunggwan Son, Jeimin Jeon, Jeongwoo Choi, Bumsub Ham

ICLR 2026poster

Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and exploiting them for subsequent steps to reduce redundant computations. Recent forecasting-based caching approaches employ temporal extrapo…

Cited by 0 Source ↗Scholar ↗

2025

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

Seunghoon Lee, Jeongwoo Choi, Byunggwan Son, Jaehyeon Moon, Jeimin Jeon, Bumsub Ham

NeurIPS 2025poster

We present in this paper a novel post-training quantization (PTQ) method, dubbed AccuQuant, for diffusion models. We show analytically and empirically that quantization errors for diffusion models are accumulated over denoising steps in a sampling process. To alleviate the error accumulation problem…

Cited by 0 Source ↗Scholar ↗