Xi Yang

ianyeung's activity

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

liked a model about 15 hours ago

facebook/sam3.1

Mask Generation • Updated 5 days ago • 3.47k • 104

upvoted a paper about 15 hours ago

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Paper • 2603.28088 • Published 3 days ago • 58

upvoted a paper about 18 hours ago

CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Paper • 2603.29664 • Published 1 day ago • 28

upvoted 3 papers about 19 hours ago

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Paper • 2603.29620 • Published 1 day ago • 33

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Paper • 2603.26599 • Published 5 days ago • 43

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published 4 days ago • 116

upvoted a paper 1 day ago

Gen-Searcher: Reinforcing Agentic Search for Image Generation

Paper • 2603.28767 • Published 2 days ago • 50

upvoted a paper 2 days ago

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published 2 days ago • 19

liked a model 2 days ago

Skywork/Matrix-Game-3.0

Image-Text-to-Video • Updated 5 days ago • 81

upvoted a paper 2 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published 6 days ago • 145

liked a model 6 days ago

RealRestorer/RealRestorer

Updated 4 days ago • 592 • 47

upvoted a paper 6 days ago

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Paper • 2603.25502 • Published 6 days ago • 55

liked a model 6 days ago

meituan-longcat/LongCat-Next

Any-to-Any • 74B • Updated 2 days ago • 1.13k • 135

liked 2 models 8 days ago

FunAudioLLM/PrismAudio

Updated 9 days ago • 69

GAIR/daVinci-MagiHuman

Image-to-Video • Updated 7 days ago • 617 • 282

upvoted a paper 9 days ago

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 9 days ago • 119

liked a model 10 days ago

Kunbyte/ROSE

Video-to-Video • Updated Sep 4, 2025 • 81 • 19

liked 2 datasets 13 days ago

Kunbyte/ROSE-Dataset

Viewer • Updated Oct 11, 2025 • 50.3k • 16.5k • 8

FudanCVL/EffectErase

Viewer • Updated 6 days ago • 781k • 1.6k • 10

liked a model 14 days ago

KlingTeam/MemFlow

Text-to-Video • Updated Dec 29, 2025 • 11