hexianyi

pkuhexianyi's activity

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

upvoted a paper 2 days ago

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Paper • 2601.17124 • Published 6 days ago • 30

upvoted a paper 7 days ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 212

upvoted a paper 29 days ago

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

Paper • 2512.21185 • Published Dec 24, 2025 • 30

upvoted a collection 3 months ago

Emu3.5

Collection

Native Multimodal Models are World Learners 🌍 • 4 items • Updated Dec 25, 2025 • 73

New activity in BestWishYsh/OpenS2V-5M 6 months ago

Fix background image paths

2

#5 opened 6 months ago by

pkuhexianyi

liked a dataset 6 months ago

BestWishYsh/OpenS2V-5M

Updated 23 days ago • 19.8k • 23

upvoted a paper 8 months ago

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

Paper • 2506.03147 • Published Jun 3, 2025 • 58

authored a paper 8 months ago

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

Paper • 2505.20292 • Published May 26, 2025 • 52

upvoted 2 papers 8 months ago

ImgEdit: A Unified Image Editing Dataset and Benchmark

Paper • 2505.20275 • Published May 26, 2025 • 18

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

Paper • 2505.20292 • Published May 26, 2025 • 52

updated a dataset 8 months ago

BestWishYsh/OpenS2V-5M

Updated 23 days ago • 19.8k • 23

authored a paper 9 months ago

Open-Sora Plan: Open-Source Large Video Generation Model

Paper • 2412.00131 • Published Nov 28, 2024 • 33

liked a dataset 9 months ago

BestWishYsh/OpenS2V-Eval

Preview • Updated 23 days ago • 932 • 5

upvoted a collection 9 months ago

OpenS2V-Nexus

Collection

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation • 5 items • Updated May 28, 2025 • 3

liked a model 9 months ago

pkuhexianyi/ConsisID-Windows

Updated Dec 7, 2024 • 3

upvoted a paper 9 months ago

Open-Sora Plan: Open-Source Large Video Generation Model

Paper • 2412.00131 • Published Nov 28, 2024 • 33

published 2 datasets 9 months ago

pkuhexianyi/test_consisid

Updated May 16, 2025

BestWishYsh/OpenS2V-5M

Updated 23 days ago • 19.8k • 23

updated a model about 1 year ago

pkuhexianyi/ConsisID-Windows

Updated Dec 7, 2024 • 3

authored a paper about 1 year ago

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

Paper • 2411.17440 • Published Nov 26, 2024 • 37