ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework
Paper • 2603.20644 • Published • 5 •
1
Ujjwal Tyagi
Ujjwal-Tyagi
AI & ML interests
Chief Scientist at Shirova AI, focused on advancing open-source AI, Experienced in LLM fine-tuning, model architecture, and research, with a strong interest in building scalable and efficient models
Recent Activity
liked a dataset 2 days ago
a3xrfgb/gpt-image-mega-4k liked a model 3 days ago
Zyphra/ZAYA1-8B liked a dataset 3 days ago
1aurent/BACHOrganizations
commented 6
papers 15 days ago
EditCaption: Human-Aligned Instruction Synthesis for Image Editing via Supervised Fine-Tuning and Direct Preference Optimization
Paper • 2604.08213 • Published • 1 •
1
ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning
Paper • 2603.08059 • Published • 1 •
1
OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution
Paper • 2603.12811 • Published • 1 •
1
Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation
Paper • 2602.13585 • Published • 1 •
1
Coevolving Representations in Joint Image-Feature Diffusion
Paper • 2604.17492 • Published • 5 •
3
It is actually the reasoning trace of gpt 5.5?
5
#1 opened 18 days ago
by Ujjwal-Tyagi
Pending Access Request to Join HF Blog Explorers
1
#17 opened 26 days ago
by 
AINovice2005
commented 5
papers about 1 month ago
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 52 •
14
Nice Work
#2 opened about 1 month ago
by Ujjwal-Tyagi
commented a
paper about 2 months ago
Sources of these data?
#2 opened 2 months ago
by Ujjwal-Tyagi
commented 4
papers 2 months ago
FireRed-OCR Technical Report
Paper • 2603.01840 • Published • 6 •
2
LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
Paper • 2602.11564 • Published • 1 •
1
Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
Paper • 2602.14027 • Published • 1 •
1
VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
Paper • 2602.04202 • Published • 1 •
1