Related papers: Rethinking Video Generation Model for the Embodied…
Text-to-video (T2V) models have shown remarkable performance in generating visually reasonable scenes, while their capability to leverage world knowledge for ensuring semantic consistency and factual accuracy remains largely understudied.…
Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests…
Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving,…
World Generation Models are emerging as a cornerstone of next-generation multimodal intelligence systems. Unlike traditional 2D visual generation, World Models aim to construct realistic, dynamic, and physically consistent 3D/4D worlds from…
The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pioneering comprehensive and scalable benchmark designed to…
While current video generation focuses on text or image conditions, practical applications like video editing and vlogging often need to seamlessly connect separate clips. In our work, we introduce Video Connecting, an innovative task that…
The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…
Recent advances in video generation models demonstrate their potential as world simulators, but they often struggle with videos deviating from physical laws, a key concern overlooked by most text-to-video benchmarks. We introduce a…
While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive…
Physical AI aims to develop models that can perceive and predict real-world dynamics; yet, the extent to which current multi-modal large language models and video generative models support these abilities is insufficiently understood. We…
Multimodal reward models (MRMs) play a crucial role in the training, inference, and evaluation of Large Vision Language Models (LVLMs) by assessing response quality. However, existing benchmarks for evaluating MRMs in the video domain…
Video generation models have achieved remarkable progress in creating high-quality, photorealistic content. However, their ability to accurately simulate physical phenomena remains a critical and unresolved challenge. This paper presents…
The enhancement of generalization in robots by large vision-language models (LVLMs) is increasingly evident. Therefore, the embodied cognitive abilities of LVLMs based on egocentric videos are of great interest. However, current datasets…
We introduce DreamGen, a simple yet highly effective 4-stage pipeline for training robot policies that generalize across behaviors and environments through neural trajectories - synthetic robot data generated from video world models.…
Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation…
World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have…
Thanks to recent advancements in scalable deep architectures and large-scale pretraining, text-to-video generation has achieved unprecedented capabilities in producing high-fidelity, instruction-following content across a wide range of…
With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image detection methods have partially addressed these concerns, a…
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…
We present a challenging new benchmark and learning-environment for robot learning: RLBench. The benchmark features 100 completely unique, hand-designed tasks ranging in difficulty, from simple target reaching and door opening, to longer…