3 21 24

Huang

Jinfa

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

authored a paper 8 days ago

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

upvoted a paper 9 days ago

ImgEdit: A Unified Image Editing Dataset and Benchmark

View all activity

Organizations

Jinfa's activity

upvoted a paper 1 day ago

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Paper • 2506.03147 • Published 2 days ago • 51

authored a paper 8 days ago

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

Paper • 2505.20292 • Published 10 days ago • 52

upvoted 2 papers 9 days ago

ImgEdit: A Unified Image Editing Dataset and Benchmark

Paper • 2505.20275 • Published 10 days ago • 17

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

Paper • 2505.20292 • Published 10 days ago • 52

upvoted a paper 23 days ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published 25 days ago • 143

commented a paper 3 months ago

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

Paper • 2503.08689 • Published Mar 11 • 4 •

upvoted a paper 3 months ago

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

Paper • 2503.08689 • Published Mar 11 • 4

upvoted 2 papers 5 months ago

VideoAuteur: Towards Long Narrative Video Generation

Paper • 2501.06173 • Published Jan 10 • 34

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Paper • 2501.09732 • Published Jan 16 • 72

liked a model 5 months ago

BestWishYsh/MagicTime

Text-to-Video • Updated Apr 12 • 29

upvoted a paper 5 months ago

Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion

Paper • 2501.09019 • Published Jan 15 • 12

liked a Space 6 months ago

Newborn Article Impact Predict

💻

Use title and abstract to predict future academic impact

liked a dataset 6 months ago

BestWishYsh/ConsisID-preview-Data

Viewer • Updated 12 days ago • 31.9k • 463 • 22

liked a model 6 months ago

BestWishYsh/ConsisID-preview

Text-to-Video • Updated Apr 10 • 273 • 27

liked a Space 6 months ago

ConsisID-preview

🔥

Identity-Preserving Text-to-Video Generation

upvoted a paper 6 months ago

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

Paper • 2411.17440 • Published Nov 26, 2024 • 38

authored a paper 6 months ago

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

Paper • 2411.17440 • Published Nov 26, 2024 • 38

liked a dataset 6 months ago

Xkev/LLaVA-CoT-100k

Viewer • Updated Nov 27, 2024 • 98.6k • 1.82k • 91

upvoted 2 papers 6 months ago

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

Paper • 2411.15411 • Published Nov 23, 2024 • 8

VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models

Paper • 2411.17451 • Published Nov 26, 2024 • 11