Related papers: Physion-Eval: Evaluating Physical Realism in Gener…
The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as potential world simulators. However, a critical gap still remains between the theoretical…
The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fine-grained hand-object interactions, track object state…
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…
Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluating whether language models can produce spatially correct animated outputs remains an…
First-person video highlights a camera-wearer's activities in the context of their persistent environment. However, current video understanding approaches reason over visual features from short video clips that are detached from the…
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…
Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natural video generation, design animation imposes structured constraints: specific components…
Reliable procedural monitoring in video requires exposure to naturally occurring human errors and the recoveries that follow. In egocentric recordings, mistakes are often partially occluded by hands and revealed through subtle object state…
AI video generation is evolving rapidly. For video generators to be useful for applications ranging from robotics to film-making, they must consistently produce realistic videos. However, evaluating the realism of generated videos remains a…
Video reasoning models are a core component of egocentric and embodied agents. However, standard benchmarks for assessing models provide only evaluation of the output (e.g. the answer to a question), without evaluation of intermediate…
The generative model has made significant advancements in the creation of realistic videos, which causes security issues. However, this emerging risk has not been adequately addressed due to the absence of a benchmark dataset for…
Despite recent advances in text-conditioned 3D indoor scene generation, there remain gaps in the evaluation of these methods. Existing metrics often measure realism by comparing generated scenes to a set of ground-truth scenes, but they…
Talking head generation is to generate video based on a given source identity and target motion. However, current methods face several challenges that limit the quality and controllability of the generated videos. First, the generated face…
We introduce FEEL (Force-Enhanced Egocentric Learning), the first large-scale dataset pairing force measurements gathered from custom piezoresistive gloves with egocentric video. Our gloves enable scalable data collection, and FEEL contains…
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…
Generative models often use human evaluations to measure the perceived quality of their outputs. Automated metrics are noisy indirect proxies, because they rely on heuristics or pretrained embeddings. However, up until now, direct human…
Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motion governed by kinematic and geometric constraints. In these settings, object parts must…
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…
Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be…
Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions. Existing tasks in egocentric perception focus on…