45 citations · 61 across the 10 of their papers we have counts for
8 papers · 1 filter
FlowBench: Counterfactual Imagination Training for Spatial Intelligence
Yifan Liu, Baihan Zhang, Khai Loong Aw +2
Humans imagine scene changes under hypothetical motions, an ability central to spatial reasoning and robotic planning. However, this capability remains underexplored in vision-lang…
Unified 3D Scene Understanding Through Physical World Modeling
Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh +4
Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essent…
Characterizing the visual representation of objects from the child's view
Jane Yang, Tarun Sepuri, Alvin Wei Ming Tan +3
Children acquire object category representations from their everyday experiences in the first few years of life. What do the inputs to this learning process look like? We analyzed…
Assessing the alignment between infants' visual and linguistic experience using multimodal language models
Alvin Wei Ming Tan, Jane Yang, Tarun Sepuri +6
Figuring out which objects or concepts words refer to is a central language learning challenge for young children. Most models of this process posit that children learn early objec…
World Modeling with Probabilistic Structure Integration
Klemen Kotar, Wanhee Lee, Rahul Venkatesh +13
We present Probabilistic Structure Integration (PSI), a system for learning richly controllable and flexibly promptable world models from data. PSI consists of a three-step cycle.…
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…
3D Scene Understanding Through Local Random Access Sequence Modeling
Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh +4
3D scene understanding from single images is a pivotal problem in computer vision with numerous downstream applications in graphics, augmented reality, and robotics. While diffusio…
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…