Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training Paper • 2608.24680 • Published 4 days ago • 9
Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper • 2608.16590 • Published 12 days ago • 147
aDSL: Agentic 3D Creation via Joint Agent-Program Design Paper • 2608.17975 • Published 11 days ago • 5
TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation Paper • 2608.16765 • Published 12 days ago • 13
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling Paper • 2608.14783 • Published 15 days ago • 19
DarwinX: Evolving Agent Harnesses Through Natural Selection Paper • 2608.07545 • Published 29 days ago • 113
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? Paper • 2608.15265 • Published 14 days ago • 59
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design Paper • 2608.13560 • Published 16 days ago • 55
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review Paper • 2608.08975 • Published 19 days ago • 48
HumanCLAW: Can Vision-Language Models Act Through a Body? Paper • 2607.27180 • Published about 1 month ago • 76
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs Paper • 2605.09635 • Published Jul 23 • 64
AlayaWorld: Long-Horizon and Playable Video World Generation Paper • 2607.06291 • Published Jul 7 • 92
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Paper • 2607.02517 • Published Jul 2 • 33