PhyGround is a new benchmark with curated prompts, a 13-law taxonomy, large-scale human annotations, and an open physics-specialized VLM judge for evaluating physical reasoning in generative video models.
Towards world simulator: Crafting physical commonsense-based benchmark for video generation
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
background 1representative citing papers
Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors.
AnimationBench is the first benchmark that operationalizes the twelve basic principles of animation and IP preservation into scalable, VLM-assisted metrics for animation-style I2V generation.
The paper presents WorldReasonBench, a benchmark that tests video generators on maintaining physical, social, logical, and informational consistency when predicting future states from initial conditions and actions.
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
SceneScribe-1M is a new dataset of 1 million videos with semantic text, camera parameters, dense depth, and consistent 3D point tracks to support monocular depth estimation, scene reconstruction, point tracking, and text-to-video synthesis.
MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts.
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
citing papers explorer
-
PhyGround: Benchmarking Physical Reasoning in Generative World Models
PhyGround is a new benchmark with curated prompts, a 13-law taxonomy, large-scale human annotations, and an open physics-specialized VLM judge for evaluating physical reasoning in generative video models.
-
Do Joint Audio-Video Generation Models Understand Physics?
Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors.
-
AnimationBench: Are Video Models Good at Character-Centric Animation?
AnimationBench is the first benchmark that operationalizes the twelve basic principles of animation and IP preservation into scalable, VLM-assisted metrics for animation-style I2V generation.
-
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
The paper presents WorldReasonBench, a benchmark that tests video generators on maintaining physical, social, logical, and informational consistency when predicting future states from initial conditions and actions.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
SceneScribe-1M is a new dataset of 1 million videos with semantic text, camera parameters, dense depth, and consistent 3D point tracks to support monocular depth estimation, scene reconstruction, point tracking, and text-to-video synthesis.
-
MAGI-1: Autoregressive Video Generation at Scale
MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts.
-
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.