xziayro

xziayro's activity

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

upvoted a paper about 20 hours ago

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

Paper • 2604.19254 • Published 4 days ago • 27

upvoted a paper about 23 hours ago

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

Paper • 2512.21185 • Published Dec 24, 2025 • 32

upvoted 2 papers 1 day ago

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

Paper • 2604.21689 • Published 2 days ago • 18

Seeing Fast and Slow: Learning the Flow of Time in Videos

Paper • 2604.21931 • Published 2 days ago • 14

upvoted a paper 2 days ago

ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis

Paper • 2604.19720 • Published 4 days ago • 3

upvoted 7 papers 3 days ago

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

Paper • 2604.18168 • Published 5 days ago • 94

UniMesh: Unifying 3D Mesh Understanding and Generation

Paper • 2604.17472 • Published 6 days ago • 9

Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items

Paper • 2604.19748 • Published 4 days ago • 243

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing

Paper • 2604.19587 • Published 4 days ago • 43

CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

Paper • 2604.19636 • Published 4 days ago • 82

Speculative Decoding for Autoregressive Video Generation

Paper • 2604.17397 • Published 6 days ago • 9

AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model

Paper • 2604.19747 • Published 4 days ago • 37

upvoted a paper 5 days ago

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Paper • 2603.25745 • Published 30 days ago • 16

upvoted 2 papers 8 days ago

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Paper • 2604.15311 • Published 9 days ago • 12

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 10 days ago • 110

upvoted an article 9 days ago

view article

Article

Nucleus-Image: Scaling Text-to-Image with Sparse Mixture of Experts

• 

11 days ago

•

9

upvoted a paper 10 days ago

Nucleus-Image: Sparse MoE for Image Generation

Paper • 2604.12163 • Published 11 days ago • 11

upvoted an article 10 days ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

Dec 1, 2025

•

310

upvoted a paper 10 days ago

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2604.12374 • Published 11 days ago • 36

upvoted a paper 15 days ago

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published 16 days ago • 51