OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining Paper • 2609.07398 • Published 4 days ago • 63
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published Aug 6 • 63
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published Jul 29 • 72
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation Paper • 2606.26907 • Published Jun 25 • 55
DreamX-World 1.0: A General-Purpose Interactive World Model Paper • 2606.16993 • Published Jun 15 • 116
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence Paper • 2606.14777 • Published Jun 10 • 217
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published Jun 11 • 113
Echo-Memory: A Controlled Study of Memory in Action World Models Paper • 2606.09803 • Published Jun 8 • 33
Native Multimodal Model Zoo Collection Native Multimodal Model Zoo is a curated collection of native multimodal models for seamless understanding and generation across diverse modalities. • 15 items • Updated Jun 5 • 2
Unified Multimodal Model Zoo Collection Unified Multimodal Model Zoo is a curated collection of UMMs that bridge understand and generation through a shared multimodal architecture. • 59 items • Updated Jun 5 • 2
3D Model Zoo Collection 3D Model Zoo is a curated collection of 3D generative models for capability exploration and systematic evaluation. • 39 items • Updated Jun 5 • 2
Video Model Zoo Collection Video Model Zoo is a curated collection of video generative models for capability exploration and systematic evaluation. • 105 items • Updated Jun 5 • 1
World Model Zoo Collection World Model Zoo is a curated collection of generative world models for interactive exploration and systematic evaluation. • 45 items • Updated Jun 5 • 2
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria Paper • 2605.08354 • Published May 8 • 23
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published Apr 15 • 127
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published Apr 15 • 171
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents Paper • 2604.07429 • Published Apr 8 • 123