← Search

Seonghye Cho

2 accepted papers

2026

Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

CVPR 2026

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism suffer from noticeable generation artifacts and fail to achie

Cited by 0SourcecodeScholar
2025

SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent

NAACL 2025long

Existing methods for simulating individual identities often oversimplify human complexity, which may lead to incomplete or flattened representations. To address this, we introduce SPeCtrum, a grounded framework for constructing authentic LLM agent personas by incorporating an individual’s multidimen…