Author

Seungryong Kim

h-index 11 View on Semantic Scholar

We have 3 of 24 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Can Learning to Answer Spatial Questions Improve Novel-View Generation?

This work introduces Ask4NV, a pretrained unified multimodal model with a Mixture-of-Transformers (MoT) architecture that incorporates camera geometry into both VAE and ViT representations and leverages understanding features during generation through joint self-attention with a modality-aware attention masking strateg...

Jahyeok Koo, Hyeonseo Yu, Seung-Ho Jang et al. · 0 citations

#computer vision Preprint Sep 2026

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they struggle to integrate evidence across viewpoints into a coherent 3D understanding. A growing body of work attempts to close th...

Jaewoo Jung, Hyeonseo Yu, Honggyu An et al. · 0 citations

Preprint Jul 2026

Transferability Between Understanding and Generation in Unified Multimodal Models

This work empirically finds that transferability depends on architecture-models with fully shared transformer backbone and a unified visual encoder exhibit consistent cross-task transfer, while loosely coupled designs show little or none.

Jiwon Kang, Heeji Yoon, Jaewoo Jung et al. · 1 citation