Huiwon Jang
7 papers · 2023–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Silver
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(15)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
representation learning
(3)
video understanding
(2)
diffusion model
(2)
self-supervised learning
(2)
image generation
(1)
video segmentation
(1)
motion estimation
(1)
temporal information
(1)
object tracking
(1)
instance segmentation
(1)
occlusion handling
(1)
text-to-image model
(1)
visual encoder
(1)
masked autoencoder
(1)
long video generation
(1)
temporal coherence
(1)
diffusion transformer
(1)
video point tracking
(1)
instance motion estimation
(1)
joint point tracking
(1)
Papers
Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
CVPR 2025
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
ICLR 2025
Adversarial Robustification via Text-to-Image Diffusion Models
ECCV 2024
TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
NeurIPS 2024
Visual Representation Learning with Stochastic Frame Prediction
ICML 2024
Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder
NeurIPS 2023
Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
ICLR 2023