Dongyu Yan

StarYDY's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 9 hours ago

blockdit/original_dit

Updated about 9 hours ago

published a model about 10 hours ago

blockdit/original_dit

Updated about 9 hours ago

authored a paper about 1 month ago

A Mechanistic View on Video Generation as World Models: State and Dynamics

Paper • 2601.17067 • Published Jan 22 • 9

upvoted a paper about 1 month ago

A Mechanistic View on Video Generation as World Models: State and Dynamics

Paper • 2601.17067 • Published Jan 22 • 9

authored a paper 2 months ago

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

Paper • 2512.21185 • Published Dec 24, 2025 • 31

liked a model 2 months ago

infinith/UltraShape

Image-to-3D • Updated Jan 31 • 99

upvoted a paper 2 months ago

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

Paper • 2512.21185 • Published Dec 24, 2025 • 31

submitted a paper to Daily Papers 2 months ago

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

Paper • 2512.21185 • Published Dec 24, 2025 • 31

liked a model 2 months ago

nvidia/NitroGen

Reinforcement Learning • Updated 28 days ago • 515

liked a Space 2 months ago

Running on Zero

178

HunyuanWorld-Mirror

🌍

178

Universal 3D World Reconstruction with Any Prior Prompting

upvoted 10 papers 3 months ago

StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors

Paper • 2512.16915 • Published Dec 18, 2025 • 38

OmniPSD: Layered PSD Generation with Diffusion Transformer

Paper • 2512.09247 • Published Dec 10, 2025 • 48

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

Paper • 2512.09363 • Published Dec 10, 2025 • 72

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

Paper • 2512.10284 • Published Dec 11, 2025 • 26

WonderZoom: Multi-Scale 3D World Generation

Paper • 2512.09164 • Published Dec 9, 2025 • 12

COREA: Coarse-to-Fine 3D Representation Alignment Between Relightable 3D Gaussians and SDF via Bidirectional 3D-to-3D Supervision

Paper • 2512.07107 • Published Dec 8, 2025 • 9

Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation

Paper • 2512.08186 • Published Dec 9, 2025 • 23

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

Paper • 2512.08358 • Published Dec 9, 2025 • 6

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Paper • 2512.08765 • Published Dec 9, 2025 • 133

EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing

Paper • 2512.06065 • Published Dec 5, 2025 • 29