Dongyu Yan

StarYDY's activity

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

upvoted 2 papers about 3 hours ago

Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects

Paper • 2511.01294 • Published 4 days ago • 10

TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

Paper • 2511.02832 • Published 2 days ago • 7

upvoted 2 papers 4 days ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published 8 days ago • 97

OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes

Paper • 2510.26800 • Published 8 days ago • 21

upvoted 2 papers 7 days ago

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks

Paper • 2510.25760 • Published 9 days ago • 16

ODesign: A World Model for Biomolecular Interaction Design

Paper • 2510.22304 • Published 13 days ago • 22

upvoted a paper 8 days ago

PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

Paper • 2510.20155 • Published 15 days ago • 4

upvoted 2 papers 9 days ago

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

Paper • 2510.22706 • Published 12 days ago • 39

Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Paper • 2510.23607 • Published 11 days ago • 172

upvoted a paper 10 days ago

WorldGrow: Generating Infinite 3D World

Paper • 2510.21682 • Published 14 days ago • 40

upvoted a paper 11 days ago

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

Paper • 2510.19944 • Published 16 days ago • 19

upvoted 3 papers 14 days ago

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

Paper • 2510.19430 • Published 16 days ago • 44

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Paper • 2510.19338 • Published 16 days ago • 110

OmniNWM: Omniscient Driving Navigation World Models

Paper • 2510.18313 • Published 17 days ago • 9

upvoted 3 papers 15 days ago

UltraGen: High-Resolution Video Generation with Hierarchical Attention

Paper • 2510.18775 • Published 17 days ago • 16

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

Paper • 2510.18876 • Published 17 days ago • 35

Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset

Paper • 2510.16258 • Published 20 days ago • 7

upvoted 3 papers 17 days ago

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Paper • 2510.15019 • Published 22 days ago • 63

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Paper • 2510.15869 • Published 21 days ago • 44

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Paper • 2510.15742 • Published 21 days ago • 49