hexianyi

pkuhexianyi's activity

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

upvoted a paper 10 days ago

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

Paper • 2512.21185 • Published 16 days ago • 28

upvoted a collection 2 months ago

Emu3.5

Collection

Native Multimodal Models are World Learners 🌍 • 4 items • Updated 16 days ago • 72

upvoted a paper 7 months ago

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

Paper • 2506.03147 • Published Jun 3, 2025 • 58

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

upvoted a collection 8 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

upvoted a paper 8 months ago

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

Paper • 2412.00131 • Published Nov 28, 2024 • 33

upvoted a paper about 1 year ago

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Paper • 2404.05014 • Published Apr 7, 2024 • 33

upvoted a collection about 1 year ago

MagicTime

Collection

MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators • 4 items • Updated Nov 29, 2024 • 13

upvoted a paper about 1 year ago

ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

Paper • 2406.18522 • Published Jun 26, 2024 • 20

upvoted 2 collections about 1 year ago

ChronoMagic-Bench

Collection

ChronoMagic-Bench : A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation • 6 items • Updated Jul 26, 2025 • 10

ConsisID

Collection

Identity-Preserving Text-to-Video Generation by Frequency Decomposition • 4 items • Updated Dec 3, 2024 • 12

upvoted a paper about 1 year ago

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

Paper • 2411.17440 • Published Nov 26, 2024 • 37