Related papers: Inference-time Physics Alignment of Video Generati…
The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence…
Robotic world models are a promising paradigm for forecasting future environment states, yet their inference speed and the physical plausibility of generated trajectories remain critical bottlenecks, limiting their real-world applications.…
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approaches relegate world models to limited roles: they operate…
A conditional latent-diffusion based framework for solving the electromagnetic inverse scattering problem associated with microwave imaging is introduced. This generative machine-learning model explicitly mirrors the non-uniqueness of the…
World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation. However, existing world models are confined to specific scenarios such as gaming or driving, limiting their…
Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsistent object motion. We introduce a frequency-domain physics…
Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges. Existing video reward models rely on vision-language models…
Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…
World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially…
Large-scale generative models have achieved remarkable success in a number of domains. However, for sequential decision-making problems, such as robotics, action-labelled data is often scarce and therefore scaling-up foundation models for…
We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…
Generative Adversarial Networks have recently shown promise for video generation, building off of the success of image generation while also addressing a new challenge: time. Although time was analyzed in some early work, the literature has…
Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced…
While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a…
Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex…
Recent video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistently-revealing a persistent gap between visual realism and…
Accurate emulation of multi-scale physical systems governed by PDEs demands models that remain stable over long autoregressive rollouts while preserving fine-scale structures. Deterministic emulators produce overly-smoothed predictions,…
Infrared imagery enables temperature-based scene understanding using passive sensors, particularly under conditions of low visibility where traditional RGB imaging fails. Yet, developing downstream vision models for infrared applications is…
Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge such as object motion, 3D geometry, and physical cues. In…