arXiv:2606. 10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood.
The paper introduces RIG-BENCH, a benchmark for evaluating reasoning-driven image generation (RIG) in four cognitively demanding domains—Concept-based, Transformation-based, Pattern & Structure, and Scenario-based—using 2000 curated samples. It highlights a reasoning-generation gap in current unified generative models (UGMs) and world simulators, noting that these models often produce locally plausible but globally illogical outputs. RIG-BENCH aims to serve as a rigorous stress test and diagnostic framework to guide the development of next-generation, logically grounded UGMs and simulators.
Ego2Act is a new benchmark that tests video generation models on goal‑directed, egocentric manipulation tasks. It contains 2,640 videos from 110 real‑world tasks, each requiring multiple steps of object manipulation to achieve a high‑level goal. The benchmark includes Ego2ActJudge, a reference‑free evaluation pipeline that better aligns with human judgments of task completion and physics plausibility.
PhysPlan is a training‑free guidance framework that enhances video diffusion models by incorporating physical awareness through agentic physics simulation. It uses a vision‑language model to generate a Chain‑of‑Visual‑Thought representation of kinematic trajectories and 3D depth, which then drives an object‑centric test‑time optimization that isolates kinematic changes and locks the passive environment. The framework also employs Kinetic Intensity Profiling to adapt hyperparameters to varying physical deformations, and demonstrates superior performance on PhyGenBench and Physics‑IQ benchmarks compared to existing VDM baselines.
arXiv:2512.14691v3 Announce Type: replace Abstract: Modern multimodal generative models can synthesize visually compelling images and videos, but it remains unclear whether this visual fluency reflec...
arXiv:2610.09514v1 Announce Type: new Abstract: Physical world modeling requires predicting how interactions change a scene, not merely generating coherent motion. We propose STRIKE, a framework that...
WorldCast is a benchmark that tests multimodal generative models on multi-step world state prediction, requiring them to forecast successive future states from multimodal observations and diverse references. The study evaluates 12 models across 320 manually designed cases in eight categories, revealing that advanced models like GPT-Image-2.5 achieve high scores while open-source models lag behind, especially on complex context and reasoning tasks. The results underscore the importance of integrating dynamic planning, reasoning, and unified multimodal capabilities for realistic world simulation.
The paper introduces Physically Plausible Video Generation (PPVG), a method that generates videos consistent with physical laws by treating physical evolution as a chain of causally connected events. It employs three modules: Physics-driven Event Chain Reasoning to decompose phenomena into scene-graph events, Transition-aware Routed Keyframe Conditioning to guide keyframe synthesis for smooth transitions, and Physics-injected Contrastive Semantic Guidance to steer generation toward plausible dynamics. Experiments on multiple physics benchmarks show improved physical plausibility compared to prior approaches.
We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors.
arXiv:2608.29910v1 Announce Type: new Abstract: Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling appli...
TourPhysics is an online framework that builds physics‑grounded visual world models from a single image and a declarative physical configuration. It integrates deterministic simulation with video generation, separating simulator state, geometric evidence, generator controls, and appearance memory to produce consistent observations for exploration and manipulation. The system preserves the input scene, follows prescribed camera and object trajectories more closely than baselines, and reduces appearance drift during long‑horizon revisits.
arXiv:2607. 04112v1 Announce Type: cross Abstract: Multimodal LLMs struggle to systematically model the temporal evolution of visual scenes in videos or multi-image sequences.