collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model

John Won, Kyungmin Lee, Huiwon Jang +2

Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predicting states and actions due to the…

cs.CV2026

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

Byungwoo Jeon, Dongyoung Kim, Huiwon Jang +2

Despite the remarkable success of large-scale pre-trained image representation models (i.e., vision encoders) across various vision tasks, they are predominantly trained on 2D imag…

cs.CV2025

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Sihyun Yu, Sangkyung Kwak, Huiwon Jang +4

Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of…

cs.CV2025

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction

Huiwon Jang, Sihyun Yu, Jinwoo Shin +2

Efficient tokenization of videos remains a challenge in training vision models that can process long videos. One promising direction is to develop a tokenizer that can encode long…

cs.CV2024

Visual Representation Learning with Stochastic Frame Prediction

Huiwon Jang, Dongyoung Kim, Junsu Kim +3

Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature…

cs.CV2024

Adversarial Robustification via Text-to-Image Diffusion Models

Daewon Choi, Jongheon Jeong, Huiwon Jang +1

Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data. In the recent paradigm of adopti…