magicwpf

magicwpf's activity

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

upvoted a paper 4 days ago

Position: Interactive Generative Video as Next-Generation Game Engine

Paper • 2503.17359 • Published 7 days ago • 57

authored a paper 5 days ago

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Paper • 2503.14487 • Published 10 days ago • 27

upvoted a paper 8 days ago

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Paper • 2503.14487 • Published 10 days ago • 27

authored 15 papers 11 days ago

SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs

Paper • 2408.11813 • Published Aug 21, 2024 • 12

MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding

Paper • 2410.21747 • Published Oct 29, 2024

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

Paper • 2412.07760 • Published Dec 10, 2024 • 55

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Paper • 2412.07759 • Published Dec 10, 2024 • 18

StyleMaster: Stylize Your Video with Artistic Generation and Translation

Paper • 2412.07744 • Published Dec 10, 2024 • 19

VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing

Paper • 2411.15260 • Published Nov 22, 2024

Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation

Paper • 2411.14423 • Published Nov 21, 2024

Towards Precise Scaling Laws for Video Diffusion Transformers

Paper • 2411.17470 • Published Nov 25, 2024 • 1

DVIS++: Improved Decoupled Framework for Universal Video Segmentation

Paper • 2312.13305 • Published Dec 20, 2023

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning

Paper • 2501.04698 • Published Jan 8 • 15

GameFactory: Creating New Games with Generative Interactive Videos

Paper • 2501.08325 • Published Jan 14 • 65

Improving Video Generation with Human Feedback

Paper • 2501.13918 • Published Jan 23 • 49

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Paper • 2502.08639 • Published Feb 12 • 42

RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification

Paper • 2503.02537 • Published 25 days ago • 11

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 14 days ago • 123

upvoted a paper 12 days ago

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 14 days ago • 123

upvoted a paper about 1 month ago

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Paper • 2502.08639 • Published Feb 12 • 42