Related papers: VideoPhy-2: A Challenging Action-Centric Physical …
This is a short technical report describing the winning entry of the PhysicsIQ Challenge, presented at the Perception Test Workshop at ICCV 2025. State-of-the-art video generative models exhibit severely limited physical understanding, and…
Video generators are increasingly evaluated as potential world models, which requires them to encode and understand physical laws. We investigate their representation of a fundamental law: gravity. Out-of-the-box video generators…
Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories:…
Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely on text prompts for evaluation, which often require complex…
Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling…
Recent advances in video generation models have sparked interest in world models capable of simulating realistic environments. While navigation has been well-explored, physically meaningful interactions that mimic real-world forces remain…
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…
Autonomous driving requires robust perception models trained on high-quality, large-scale multi-view driving videos for tasks like 3D object detection, segmentation and trajectory prediction. While world models provide a cost-effective…
The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models.…
Discovering physical laws directly from high-dimensional visual data is a long-standing human pursuit but remains a formidable challenge for machines, representing a fundamental goal of scientific intelligence. This task is inherently…
Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing…
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.…
State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts rather than model limitations: manually adding physics…
We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e.g., force and torque applied to an object in the image) to produce a realistic, physically plausible, and temporally…
Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that…
With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap,…
World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse…
Deep video action recognition models have been highly successful in recent years but require large quantities of manually annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic…
Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently…
Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However, emerging evidence suggests that simply scaling data and model size does not endow…