45 citations · 61 across the 10 of their papers we have counts for
13 papers
-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model
Khai Loong Aw, Klemen Kotar, Baihan Zhang +5
Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabili…
Scaling cross-situational word learning on children's naturalistic experiences
Michael C. Frank, Alvin W. M. Tan, Khai Loong Aw +9
How do children learn the meanings of the simple, concrete words that form a majority of their early vocabulary? Statistical information about many word meanings can be recovered f…
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…
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…
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…
Instruction-tuning Aligns LLMs to the Human Brain
Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi +2
Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studi…
Training language models to summarize narratives improves brain alignment
Khai Loong Aw, Mariya Toneva
Building systems that achieve a deeper understanding of language is one of the central goals of natural language processing (NLP). Towards this goal, recent works have begun to tra…
Detecting False Alarms from Automatic Static Analysis Tools: How Far are We?
Hong Jin Kang, Khai Loong Aw, David Lo
Automatic static analysis tools (ASATs), such as Findbugs, have a high false alarm rate. The large number of false alarms produced poses a barrier to adoption. Researchers have pro…