SongFei

Xsong123's activity

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

upvoted a paper 16 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 17 days ago • 138

upvoted a paper 2 months ago

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Paper • 2607.07820 • Published Jul 8 • 95

updated a dataset 3 months ago

Kontext-Style/qwen-image-bench-2step-gan-ablation

Updated Jul 16 • 8

published a dataset 3 months ago

Kontext-Style/qwen-image-bench-2step-gan-ablation

Updated Jul 16 • 8

updated 2 datasets 3 months ago

Xsong123/lucidreward

Preview • Updated Jul 12 • 2

Kontext-Style/gpt-image-2-zq10k-2048

Viewer • Updated Jul 11 • 10k • 26 • 1

published a dataset 3 months ago

Kontext-Style/gpt-image-2-zq10k-2048

Viewer • Updated Jul 11 • 10k • 26 • 1

liked a dataset 3 months ago

Owen777/HQ-OpenHumanVid

Viewer • Updated Nov 18, 2025 • 1.2M • 27.1k • 7

upvoted a paper 3 months ago

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Paper • 2606.19534 • Published Jun 17 • 66

updated a model 4 months ago

W2GenAI/LucidFlux

Image-to-Image • Updated May 26 • 30

liked a model 6 months ago

madebyollin/taef2

Updated Jan 19 • 27

published a model 7 months ago

W2GenAI/LucidNFT

Updated Mar 13

updated a model 7 months ago

W2GenAI/LucidNFT

Updated Mar 13

New activity in sgdkn/pose-classification-hp 9 months ago

Code For Inference

1

#1 opened 9 months ago by

Xsong123

upvoted a paper 9 months ago

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published Jan 13 • 158

published a dataset 9 months ago

Xsong123/lucidreward

Preview • Updated Jul 12 • 2

upvoted a paper 10 months ago

Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

Paper • 2512.01030 • Published Nov 30, 2025 • 20

liked a model 10 months ago

black-forest-labs/FLUX.1-dev

Text-to-Image • 12B • Updated Jun 27, 2025 • 713k • • 15.3k

upvoted a paper 10 months ago

UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

Paper • 2511.18050 • Published Nov 22, 2025 • 38

liked a model 11 months ago

Owen777/UltraFlux-v1

Text-to-Image • 12B • Updated May 21 • 87 • 211