Wei Cheng

wchengad's activity

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

upvoted a paper 2 days ago

Relational Visual Similarity

Paper • 2512.07833 • Published 3 days ago • 23

upvoted a paper 3 days ago

EditThinker: Unlocking Iterative Reasoning for Any Image Editor

Paper • 2512.05965 • Published 6 days ago • 36

upvoted 3 papers 10 days ago

Captain Safari: A World Engine

Paper • 2511.22815 • Published 14 days ago • 9

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 14 days ago • 183

REASONEDIT: Towards Reasoning-Enhanced Image Editing Models

Paper • 2511.22625 • Published 14 days ago • 45

upvoted a paper 15 days ago

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

Paper • 2511.20635 • Published 16 days ago • 31

upvoted a paper 20 days ago

Step-Audio-R1 Technical Report

Paper • 2511.15848 • Published 22 days ago • 51

upvoted 3 papers about 1 month ago

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

Paper • 2511.02778 • Published Nov 4 • 101

RegionE: Adaptive Region-Aware Generation for Efficient Image Editing

Paper • 2510.25590 • Published Oct 29 • 27

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

Paper • 2510.22706 • Published Oct 26 • 39

upvoted 3 papers about 2 months ago

WithAnyone: Towards Controllable and ID Consistent Image Generation

Paper • 2510.14975 • Published Oct 16 • 84

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

Paper • 2510.11712 • Published Oct 13 • 30

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Paper • 2510.08673 • Published Oct 9 • 125

upvoted 6 papers 3 months ago

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

Paper • 2509.12815 • Published Sep 16 • 39

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

Paper • 2509.12203 • Published Sep 15 • 19

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published Sep 15 • 104

USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

Paper • 2508.18966 • Published Aug 26 • 56

Mixture of Contexts for Long Video Generation

Paper • 2508.21058 • Published Aug 28 • 35

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Paper • 2508.20751 • Published Aug 28 • 89

upvoted a paper 4 months ago

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

Paper • 2508.14111 • Published Aug 18 • 33