Related papers: WorldScore: A Unified Evaluation Benchmark for Wor…
As world models gain momentum in Embodied AI, an increasing number of works explore using video foundation models as predictive world models for downstream embodied tasks like 3D prediction or interactive generation. However, before…
Spatio-temporal scene graphs provide a principled representation for modeling evolving object interactions, yet existing methods remain fundamentally frame-centric: they reason only about currently visible objects, discard entities upon…
World models are central to building AI agents capable of flexible reasoning and planning. Yet current evaluations (i) test only properties measurable from observed interactions, such as next-frame prediction or task return, and (ii) do not…
Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these…
Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in domains such as natural image or medical imaging,…
Recent approaches have demonstrated the promise of using diffusion models to generate interactive and explorable worlds. However, most of these methods face critical challenges such as excessively large parameter sizes, reliance on lengthy…
Recipe image generation is an important challenge in food computing, with applications from culinary education to interactive recipe platforms. However, there is currently no real-world dataset that comprehensively connects recipe goals,…
We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the…
Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background…
We introduce OneDiffusion, a versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. It enables conditional generation from inputs such as text, depth, pose,…
While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…
Video diffusion models have rich world priors, but their use in spatial tasks is limited by poor control, spatial-temporal inconsistent results, and entangled scene-camera dynamics. Current approaches, such as per-task fine-tuning or…
The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to understand their potential biases. In this work, we…
Being able to edit panoramic images is crucial for creating realistic 360{\deg} visual experiences. However, existing perspective-based image editing methods fail to model the spatial structure of panoramas. Conventional cube-map…
Music scores are written representations of music and contain rich information about musical components. The visual information on music scores includes notes, rests, staff lines, clefs, dynamics, and articulations. This visual information…
Video fundamentally intertwines two crucial axes: the dynamic content of a scene and the camera motion through which it is observed. However, existing generation models often entangle these factors, limiting independent control. In this…
Recent research has been increasingly focusing on developing 3D world models that simulate complex real-world scenarios. World models have found broad applications across various domains, including embodied AI, autonomous driving,…
The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this…
Recent advances in video generation have been remarkable, enabling models to produce visually compelling videos with synchronized audio. While existing video generation benchmarks provide comprehensive metrics for visual quality, they lack…
Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark…