MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language
Paper • 2410.22367 • Published • 1 •
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
posted an update about 3 hours ago
To improve the current open-source image generation models by focusing on Indian contexts and people, I created a dataset of 100 million Indian image generation prompts. Since open-source models perform incredibly poorly in Indian contexts and for people, I created this dataset so that people can generate distillation datasets from proprietary image generation models like GPT Image 2 to improve existing open source image generation models. https://huggingface.co/datasets/Ujjwal-Tyagi/indian-image-prompts-100m updated a dataset about 6 hours ago
Ujjwal-Tyagi/indian-image-prompts-100m published a dataset about 6 hours ago
Ujjwal-Tyagi/indian-image-prompts-100mOrganizations
It is actually the reasoning trace of gpt 5.5?
11
#1 opened 21 days ago
by Ujjwal-Tyagi
commented 3
papers 1 day ago
commented 6
papers 18 days ago
ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework
Paper • 2603.20644 • Published • 5 •
1
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
Pending Access Request to Join HF Blog Explorers
2
#17 opened 30 days ago
by 
AINovice2005
commented 5
papers about 2 months ago
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53 •
14
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53 •
14
Nice Work
#2 opened about 2 months ago
by Ujjwal-Tyagi
commented a
paper about 2 months ago
Sources of these data?
#2 opened 2 months ago
by Ujjwal-Tyagi
commented a
paper 2 months ago