← Search

Youngwoo Shin

2 accepted papers

2026

SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation

ICLR 2026poster

Visual autoregressive (VAR) models generate images through next-scale prediction, naturally achieving coarse-to-fine, fast, high-fidelity synthesis mirroring human perception. In practice, this hierarchy can drift at inference time, as limited capacity and accumulated error cause the model to deviat…

Cited by 0SourcecodeScholar
2025

Memorization or Reasoning? Exploring the Idiom Understanding of LLMs

EMNLP 2025

Idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. While recent studies have leveraged large language models (LLMs) to handle idioms across various tasks, e.g., idiom-containing sentence generation and idiomatic machine t