Hugging Face's logo
Xiaotian Han's picture
2 8 9

Xiaotian Han

xiaotianhan
louisbrulenaudet's profile picture Mi6paulino's profile picture JAADARI's profile picture
·
https://hanxiaotian.github.io/

AI & ML interests

Multimodal LLM

Recent Activity

upvoted a paper 30 days ago
TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
authored a paper about 2 months ago
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
liked a model about 2 months ago
shallowdream204/DreamClear
View all activity

Organizations

InfiMM's profile picture Social Post Explorers's profile picture

Posts 3

view post
Post
880
🚀 Excited to announce the release of InfiMM-WebMath-40B — the largest open-source multimodal pretraining dataset designed to advance mathematical reasoning in AI! 🧮✨

With 40 billion tokens, this dataset aims for enhancing the reasoning capabilities of multimodal large language models in the domain of mathematics.

If you're interested in MLLMs, AI, and math reasoning, check out our work and dataset:

🤗 HF: InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning (2409.12568)
📂 Dataset: Infi-MM/InfiMM-WebMath-40B
view post
Post
2093
🎉 🎉 🎉 Happy to share our recent work. We noticed that image resolution plays an important role, either in improving multi-modal large language models (MLLM) performance or in Sora style any resolution encoder decoder, we hope this work can help lift restriction of 224x224 resolution limit in ViT.

ViTAR: Vision Transformer with Any Resolution (2403.18361)
View all posts

Papers 8

models

None public yet

datasets

None public yet