PrismWAM: Decoupling State Representations in World Action Models Paper • 2610.26564 • Published about 1 month ago • 3
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes Paper • 2610.18356 • Published Oct 13 • 115
Scaling Agentic Data for Long-Horizon Terminal Intelligence Paper • 2610.13166 • Published Oct 9 • 125
IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts Paper • 2609.21346 • Published Sep 18 • 88
OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining Paper • 2609.07398 • Published Sep 7 • 70
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation Paper • 2609.05588 • Published Sep 4 • 38
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution Paper • 2608.31106 • Published Aug 31 • 86
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering Paper • 2608.28281 • Published Aug 28 • 89
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation Paper • 2608.13489 • Published Aug 13 • 86
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model Paper • 2509.09372 • Published Sep 11, 2025 • 183
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Paper • 2608.01964 • Published Aug 3 • 168
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies Paper • 2606.15768 • Published Jun 14 • 5
Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment Paper • 2607.13941 • Published Jul 15 • 2
OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data Paper • 2606.30019 • Published Jun 29 • 19
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding Paper • 2606.31315 • Published Jun 30 • 65
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation Paper • 2606.17030 • Published Jun 15 • 47
DreamX-World 1.0: A General-Purpose Interactive World Model Paper • 2606.16993 • Published Jun 15 • 106
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution Paper • 2606.10917 • Published Jun 9 • 69
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation Paper • 2605.22355 • Published May 21 • 117
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos Paper • 2605.18233 • Published May 18 • 84