6 papers
Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
Seungwook Kim, Minsu Cho
Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models is a promising path to improve human…
Zero-shot World Models Are Developmentally Efficient Learners
Khai Loong Aw, Klemen Kotar, Wanhee Lee +6
Young children demonstrate early abilities to understand their physical world, estimating depth, motion, object coherence, interactions, and many other aspects of physical scene un…
Taming generative video models for zero-shot optical flow extraction
Seungwoo Kim, Khai Loong Aw, Klemen Kotar +8
Extracting optical flow from videos remains a core computer vision problem. Motivated by the recent success of large general-purpose models, we ask whether frozen self-supervised v…
Discovering and using Spelke segments
Rahul Venkatesh, Klemen Kotar, Lilian Naing Chen +10
Segments in computer vision are often defined by semantic considerations and are highly dependent on category-specific conventions. In contrast, developmental psychology suggests t…
Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
Stefan Stojanov, David Wendt, Seungwoo Kim +4
Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are p…
Halal or Not: Knowledge Graph Completion for Predicting Cultural Appropriateness of Daily Products
Van Thuy Hoang, Tien-Bach-Thanh Do, Jinho Seo +5
The growing demand for halal cosmetic products has exposed significant challenges, especially in Muslim-majority countries. Recently, various machine learning-based strategies, e.g…