Ujjwal Tyagi's picture

Building on HF

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 model about 2 hours ago

XiaomiMiMo/MiMo-V2.5

upvoted a paper about 4 hours ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

liked a model about 7 hours ago

stepfun-ai/Step-Audio-R1.1

View all activity

Organizations

liked a model about 2 hours ago

XiaomiMiMo/MiMo-V2.5

311B • Updated about 6 hours ago • 2.66k • 153

upvoted a paper about 4 hours ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 3 days ago • 58

liked a model about 7 hours ago

stepfun-ai/Step-Audio-R1.1

Audio-Text-to-Text • 33B • Updated Feb 14 • 293 • 175

liked a model about 8 hours ago

Qwen/Qwen-Image-2512

Text-to-Image • Updated Dec 31, 2025 • 69.4k • • 802

liked a dataset 1 day ago

InternVL-U/ScaleEdit-12M

Viewer • Updated 23 days ago • 12.4M • 12.5k • 16

upvoted a paper 1 day ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 60

commented a paper 1 day ago

ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework

Paper • 2603.20644 • Published Mar 21 • 5 •

upvoted a paper 1 day ago

ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework

Paper • 2603.20644 • Published Mar 21 • 5

commented a paper 1 day ago

EditCaption: Human-Aligned Instruction Synthesis for Image Editing via Supervised Fine-Tuning and Direct Preference Optimization

Paper • 2604.08213 • Published 21 days ago • 1 •

upvoted a paper 1 day ago

EditCaption: Human-Aligned Instruction Synthesis for Image Editing via Supervised Fine-Tuning and Direct Preference Optimization

Paper • 2604.08213 • Published 21 days ago • 1

commented a paper 1 day ago

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning

Paper • 2603.08059 • Published Mar 9 • 1 •

upvoted a paper 1 day ago

ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning

Paper • 2603.08059 • Published Mar 9 • 1

commented a paper 1 day ago

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

Paper • 2603.12811 • Published Mar 13 • 1 •

upvoted 3 papers 1 day ago

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

Paper • 2603.12811 • Published Mar 13 • 1

EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

Paper • 2603.14916 • Published Mar 16 • 1

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

Paper • 2603.12247 • Published Mar 12 • 24

upvoted a collection 1 day ago

Image Generation

Image Generation • 51 items • Updated about 13 hours ago • 1

commented a paper 1 day ago

Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation

Paper • 2602.13585 • Published Feb 27 • 1 •

upvoted 2 papers 1 day ago

Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation

Paper • 2602.13585 • Published Feb 27 • 1

Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing

Paper • 2602.08820 • Published Feb 9 • 1