Runway’s WorldPrompt and the Engineering of Real-Time Worlds
2 sources 15 min
Opus 5.5 is good at explainer videos
2 min
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
Training Object Permanence in World Models
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
1
The Past Frames the Future: Memory for Autoregressive Video Generation
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Generative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks
Higgsfield AI ships new video features in a day with GPT-6 Astra
2 min1
HappyWorld-Bench
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
VideoGen-Agent: Reinforcing Video Generation Agents
RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation
1
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model
1
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
1
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows
1