DocReward: A Document Reward Model for Structuring and Stylizing Paper • 2510.11391 • Published 24 days ago • 26
ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data Paper • 2509.15221 • Published Sep 18 • 109
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR Paper • 2508.14029 • Published Aug 19 • 118
OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion Paper • 2507.06165 • Published Jul 8 • 58
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling Paper • 2507.07982 • Published Jul 10 • 33
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft Paper • 2504.08388 • Published Apr 11 • 42
Large Motion Video Autoencoding with Cross-modal Video VAE Paper • 2412.17805 • Published Dec 23, 2024 • 24
RoLoRA Collection [EMNLP2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization • 3 items • Updated Sep 26, 2024 • 3
3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection Paper • 2410.01647 • Published Oct 2, 2024 • 31