Wei Song (SII)

Songweii's activity

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

authored 3 papers about 13 hours ago

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Paper • 2602.02437 • Published Feb 2 • 80

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published Feb 12 • 83

DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

Paper • 2605.22777 • Published 2 days ago • 1

submitted a paper to Daily Papers about 19 hours ago

DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

Paper • 2605.22777 • Published 2 days ago • 1

liked 3 datasets about 1 month ago

UCSC-VLAA/Recap-COCO-30K

Viewer • Updated Jun 12, 2024 • 30.5k • 272 • 26

xingjianleng/coco-30k

Viewer • Updated Jul 16, 2025 • 30k • 106 • 1

dylanlim78/coco-30k-val-2014

Viewer • Updated Feb 1 • 30k • 91 • 1

liked a model 3 months ago

deepgenteam/DeepGen-1.0

Text-to-Image • Updated Mar 2 • 20 • 179

upvoted a paper 3 months ago

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published Feb 12 • 83

upvoted a paper 4 months ago

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Paper • 2602.02437 • Published Feb 2 • 80

upvoted 2 papers 6 months ago

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published Dec 3, 2025 • 77

GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

Paper • 2511.15705 • Published Nov 19, 2025 • 98

upvoted a paper 7 months ago

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation

Paper • 2510.18701 • Published Oct 21, 2025 • 68

liked 6 datasets 10 months ago

LucasFang/Laion-Aesthetics-High-Resolution-GoT

Viewer • Updated Mar 18, 2025 • 3.77M • 689 • 12

limingcv/LAION_Aesthetics_512

Viewer • Updated Mar 24, 2024 • 2.81M • 4.98k • 5

gmongaras/Stable_Diffusion_3_Recaption

Viewer • Updated Jan 3, 2025 • 10.9M • 897 • 5

gmongaras/Imagenet21K

Viewer • Updated Feb 3, 2025 • 13.2M • 16.5k • 6

gmongaras/Imagenet21K_Recaption

Viewer • Updated Sep 17, 2025 • 13.1M • 526 • 10

gmongaras/CC12M_and_Imagenet21K_Recap

Viewer • Updated Sep 17, 2025 • 22.7M • 14.8k • 10

authored a paper 12 months ago

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Paper • 2506.09040 • Published Jun 10, 2025 • 34