3 19 165

JingyeChen22

https://jingyechen.github.io

JingyeChen

AI & ML interests

OCR, Document Analysis, Text-to-X

Recent Activity

liked a Space about 21 hours ago

AILab-CVC/SEED-Bench_Leaderboard

liked a Space 5 days ago

Howieeeee/WorldScore_Leaderboard

upvoted a paper 11 days ago

Video-R1: Reinforcing Video Reasoning in MLLMs

View all activity

Organizations

JingyeChen22's activity

liked a Space about 21 hours ago

SEED-Bench Leaderboard

🏆

liked a Space 5 days ago

WorldScore Leaderboard

🏆

Upload and manage evaluation data for models

upvoted a paper 11 days ago

Video-R1: Reinforcing Video Reasoning in MLLMs

Paper • 2503.21776 • Published 12 days ago • 76

liked a model 13 days ago

KumaPower/AvatarArtist

Updated 13 days ago • 3

liked a Space 18 days ago

1.9k

QR Code AI Art Generator

📱

QR Code AI Art Generator Blend QR codes with AI Art

liked a Space 22 days ago

谁是卧底Agent示例

🚀

Create and compete AI agents in a Spy game

updated a Space 26 days ago

2048

👀

published a Space 26 days ago

2048

👀

liked a Space 3 months ago

8.05k

FLUX.1 [dev]

🖥

Generate images from text prompts

liked a model 3 months ago

videophysics/videocon_physics

Updated Jun 5, 2024 • 45 • 5

liked a dataset 3 months ago

videophysics/videophy_train_public

Viewer • Updated Dec 2, 2024 • 4.59k • 77 • 1

authored a paper 3 months ago

Large Motion Video Autoencoding with Cross-modal Video VAE

Paper • 2412.17805 • Published Dec 23, 2024 • 24

upvoted a paper 4 months ago

Large Motion Video Autoencoding with Cross-modal Video VAE

Paper • 2412.17805 • Published Dec 23, 2024 • 24

upvoted a collection 4 months ago

RoLoRA

Collection

[EMNLP2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization • 3 items • Updated Sep 26, 2024 • 3

upvoted a paper 4 months ago

GenEx: Generating an Explorable World

Paper • 2412.09624 • Published Dec 12, 2024 • 96

liked 2 Spaces 4 months ago

AgentReview

🎓

EMNLP 2024

RF-Solver-Edit

🪄

High Quality Inversion and Editing of FLUX and OpenSora.

liked 2 models 4 months ago

THUDM/CogVideoX-5b

Text-to-Video • Updated Nov 23, 2024 • 62.1k • • 597

Lightricks/LTX-Video

Text-to-Video • Updated 27 days ago • 149k • • 1.11k

liked a Space 5 months ago

1.75k

MagicQuill

🪶

Edit and enhance images with custom color and edge modifications