Related papers: PhysiX: A Foundation Model for Physics Simulations

Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce…

We investigate the impact of tokeniser pretraining on the accuracy and efficiency of physics emulation. Modern high-resolution simulations produce vast volumes of data spanning diverse physical regimes and scales. Training foundation models…

Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reasoning-intensive and essential to real-world understanding,…

While current vision algorithms excel at many challenging tasks, it is unclear how well they understand the physical dynamics of real-world environments. Here we introduce Physion, a dataset and benchmark for rigorously evaluating the…

Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of…

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…

Video generation models have emerged as high-fidelity models of the physical world, capable of synthesizing high-quality videos capturing fine-grained interactions between agents and their environments conditioned on multi-modal user…

We present IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models. Building on the original IntPhys benchmark, IntPhys 2 focuses on four core principles related to macroscopic objects:…

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…

Modeling sounds emitted from physical object interactions is critical for immersive perceptual experiences in real and virtual worlds. Traditional methods of impact sound synthesis use physics simulation to obtain a set of physics…

Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation…

Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vision Language Models (VLMs), have demonstrated remarkable…

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time.…

Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled…

Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution. This makes it difficult to determine…

Visual parsing of images and videos is critical for a wide range of real-world applications. However, progress in this field is constrained by limitations of existing datasets: (1) insufficient annotation granularity, which impedes…

Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models from limited real-world video data, especially for…

3D modeling is shifting from static visual representations toward physical, articulated assets that can be directly used in simulation and interaction. However, most existing 3D generation methods overlook key physical and articulation…

We survey applications of pretrained foundation models in robotics. Traditional deep learning models in robotics are trained on small datasets tailored for specific tasks, which limits their adaptability across diverse applications. In…

Despite significant advances in video generation, synthesizing physically plausible human actions remains a persistent challenge, particularly in modeling fine-grained semantics and complex temporal dynamics. For instance, generating…