6 papers · 1 filter
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…
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…
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…
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…
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…
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…