Related papers: ContPhy: Continuum Physical Concept Learning and R…
The ability to discover abstract physical concepts and understand how they work in the world through observing lies at the core of human intelligence. The acquisition of this ability is based on compositionally perceiving the environment in…
Physical reasoning is important for effective robot manipulation. Recent work has investigated both vision and language modalities for physical reasoning; vision can reveal information about objects in the environment and language serves as…
Physical reasoning is a crucial aspect in the development of general AI systems, given that human learning starts with interacting with the physical world before progressing to more complex concepts. Although researchers have studied and…
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…
A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts…
Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and…
The autonomous evolution of networked AI systems relies heavily on robust environmental perception. However, physical understanding remains brittle in current models because key physical signals are visually ambiguous and sparsely…
Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown promising results on several commonsense benchmark datasets.…
Recent advancements in deep learning, computer vision, and embodied AI have given rise to synthetic causal reasoning video datasets. These datasets facilitate the development of AI algorithms that can reason about physical interactions…
In recent years, vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they…
In this paper, we propose a Disentangled Counterfactual Learning~(DCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects' physics commonsense based on both video and audio input, with the main challenge…
By providing substantial amounts of data and standardized evaluation protocols, datasets in computer vision have helped fuel advances across all areas of visual recognition. But even in light of breakthrough results on recent benchmarks, it…
Most learning-based approaches to complex physical reasoning sidestep the crucial problem of parameter identification (e.g., mass, friction) that governs scene dynamics, despite its importance in real-world applications such as collision…
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2…
Mastering commonsense understanding and reasoning is a pivotal skill essential for conducting engaging conversations. While there have been several attempts to create datasets that facilitate commonsense inferences in dialogue contexts,…
In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects and their interactions from videos and language. This is…
Videos often capture objects, their visible properties, their motion, and the interactions between different objects. Objects also have physical properties such as mass, which the imaging pipeline is unable to directly capture. However,…
Due to the emergence of AI systems that interact with the physical environment, there is an increased interest in incorporating physical reasoning capabilities into those AI systems. But is it enough to only have physical reasoning…
Discovering physical laws directly from high-dimensional visual data is a long-standing human pursuit but remains a formidable challenge for machines, representing a fundamental goal of scientific intelligence. This task is inherently…
Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an essential cornerstone in building general AI systems. We propose a new commonsense reasoning dataset based on human's Interactive…