Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
4
1
7
Luci
Akirami
Follow
0 followers
·
9 following
LuciAkirami
AI & ML interests
None yet
Recent Activity
liked
a Space
10 days ago
bookbot/Image-Upscaling-Playground
reacted
to
singhsidhukuldeep
's
post
with 🤗
4 months ago
Exciting breakthrough in Document AI! Researchers from UNC Chapel Hill and Bloomberg have developed M3DocRAG, a revolutionary framework for multi-modal document understanding. The innovation lies in its ability to handle complex document scenarios that traditional systems struggle with: - Process 40,000+ pages across 3,000+ documents - Answer questions requiring information from multiple pages - Understand visual elements like charts, tables, and figures - Support both closed-domain (single document) and open-domain (multiple documents) queries Under the hood, M3DocRAG operates through three sophisticated stages: >> Document Embedding: - Converts PDF pages to RGB images - Uses ColPali to project both text queries and page images into a shared embedding space - Creates dense visual embeddings for each page while maintaining visual information integrity >> Page Retrieval: - Employs MaxSim scoring to compute relevance between queries and pages - Implements inverted file indexing (IVFFlat) for efficient search - Reduces retrieval latency from 20s to under 2s when searching 40K+ pages - Supports approximate nearest neighbor search via Faiss >> Question Answering: - Leverages Qwen2-VL 7B as the multi-modal language model - Processes retrieved pages through a visual encoder - Generates answers considering both textual and visual context The results are impressive: - State-of-the-art performance on MP-DocVQA benchmark - Superior handling of non-text evidence compared to text-only systems - Significantly better performance on multi-hop reasoning tasks This is a game-changer for industries dealing with large document volumes—finance, healthcare, and legal sectors can now process documents more efficiently while preserving crucial visual context.
updated
a collection
4 months ago
JailBreak
View all activity
Organizations
Akirami
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a Space
10 days ago
Running
529
529
Image Upscaling Playground
🦆
Upscale images to enhance quality
liked
a model
4 months ago
katanemo/Arch-Guard-cpu
Text Classification
•
Updated
Jan 15
•
2.02k
•
3
liked
a model
9 months ago
mlabonne/NeuralPipe-7B-slerp
Text Generation
•
Updated
Jul 2, 2024
•
17
•
7
liked
a dataset
9 months ago
openai/gsm8k
Viewer
•
Updated
Jan 4, 2024
•
17.6k
•
331k
•
656
liked
2 models
10 months ago
CohereForAI/aya-23-8B
Text Generation
•
Updated
2 days ago
•
10.5k
•
•
410
HuggingFaceFW/fineweb-edu-classifier
Text Classification
•
Updated
Nov 17, 2024
•
86.7k
•
•
171
liked
a model
11 months ago
Akirami/truthy-llama3-8b
Text Generation
•
Updated
Apr 29, 2024
•
7
•
1