collaborators

20 papers

cs.CV2026

GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion

Yeji Choi, Jinhyeok Choi, Jaewon Min +3

We present GeoFace, a geometry-constrained multi-view diffusion framework for consistent face generation from a single input. % While recent multi-view diffusion models achieve pho…

cs.CV2026

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

Hyunmin Cho, Donghoon Ahn, Susung Hong +3

Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external…

cs.CV2026

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Jin Hyeon Kim, Jaeeun Lee, Claire Kim +8

Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated un…

cs.LG2026

Looped Diffusion Language Models

Sanghyun Lee, Chunsan Hong, Seungryong Kim +3

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDM…

cs.CV2026

WorldKV: Efficient World Memory with World Retrieval and Compression

Jung Yi, Minjae Kim, Paul Hyunbin Cho +3

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpo…

cs.CV2026

Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation

Youngdong Jang, Gyeongrok Oh, Jong Wook Kim +6

LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate t…