相关论文: VideoPhy-2: A Challenging Action-Centric Physical …
Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance.…
With AI-generated videos increasingly indistinguishable from reality, current benchmarks primarily focus on broad semantic alignment and basic physical consistency, offering limited discriminative power for evaluating them. To address this,…
Recent advancements in text-to-video (T2V) diffusion models have enabled high-fidelity and realistic video synthesis. However, current T2V models often struggle to generate physically plausible content due to their limited inherent ability…
Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality short clips but often fail to preserve entity identity and…
We introduce MultiPhys, a method designed for recovering multi-person motion from monocular videos. Our focus lies in capturing coherent spatial placement between pairs of individuals across varying degrees of engagement. MultiPhys, being…
Existing single-image 3D indoor scene generators often produce results that look visually plausible but fail to obey real-world physics, limiting their reliability in robotics, embodied AI, and design. To examine this gap, we introduce a…
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…
Automatic video summarization is still an unsolved problem due to several challenges. We take steps towards making automatic video summarization more realistic by addressing them. Firstly, the currently available datasets either have very…
AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protect individuals, organizations, and societies from its…
One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-art methods are able to synthesize a video demonstrating…
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can…
World models aim to understand, remember, and predict dynamic visual environments, yet a unified benchmark for evaluating their fundamental abilities remains lacking. To address this gap, we introduce MIND, the first open-domain closed-loop…
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…
Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video…
Understanding and reasoning about objects' physical properties in the natural world is a fundamental challenge in artificial intelligence. While some properties like colors and shapes can be directly observed, others, such as mass and…
Foundation models have achieved remarkable success across video, image, and language domains. By scaling up the number of parameters and training datasets, these models acquire generalizable world knowledge and often surpass task-specific…
Evaluating the quality of videos generated from text-to-video (T2V) models is important if they are to produce plausible outputs that convince a viewer of their authenticity. We examine some of the metrics used in this area and highlight…
Current video models fail as world model as they lack fine-graiend control. General-purpose household robots require real-time fine motor control to handle delicate tasks and urgent situations. In this work, we introduce fine-grained…
Predicting the dynamics of interacting objects is essential for both humans and intelligent systems. However, existing approaches are limited to simplified, toy settings and lack generalizability to complex, real-world environments. Recent…
Recent breakthroughs in Vision-Language (V&L) joint research have achieved remarkable results in various text-driven tasks. High-quality Text-to-video (T2V), a task that has been long considered mission-impossible, was proven feasible with…