The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding Paper • 2512.19693 • Published 8 days ago • 61
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers Paper • 2512.17351 • Published 11 days ago • 22
Make-It-Poseable: Feed-forward Latent Posing Model for 3D Humanoid Character Animation Paper • 2512.16767 • Published 12 days ago • 4
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published 13 days ago • 56
EgoX: Egocentric Video Generation from a Single Exocentric Video Paper • 2512.08269 • Published 21 days ago • 114
Multi-view Pyramid Transformer: Look Coarser to See Broader Paper • 2512.07806 • Published 22 days ago • 20
MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos Paper • 2512.10881 • Published 19 days ago • 29
StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation Paper • 2512.09363 • Published 20 days ago • 71
SIMA 2: A Generalist Embodied Agent for Virtual Worlds Paper • 2512.04797 • Published 26 days ago • 24
RELIC: Interactive Video World Model with Long-Horizon Memory Paper • 2512.04040 • Published 27 days ago • 23
Deep Unsupervised Learning using Nonequilibrium Thermodynamics Paper • 1503.03585 • Published Mar 12, 2015 • 6
From thermodynamics to protein design: Diffusion models for biomolecule generation towards autonomous protein engineering Paper • 2501.02680 • Published Jan 5 • 2
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models Paper • 2512.02556 • Published 28 days ago • 241
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning Paper • 2511.22570 • Published Nov 27 • 83
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer Paper • 2511.22699 • Published Nov 27 • 216