6 46 108

Anthony W Figueroa

THEFIG

AI & ML interests

None yet

Recent Activity

liked a model about 2 months ago

google/timesfm-2.0-500m-pytorch

reacted to singhsidhukuldeep's post with 🚀 about 2 months ago

Exciting breakthrough in Retrieval-Augmented Generation (RAG): Introducing MiniRAG - a revolutionary approach that makes RAG systems accessible for edge devices and resource-constrained environments. Key innovations that set MiniRAG apart: Semantic-aware Heterogeneous Graph Indexing - Combines text chunks and named entities in a unified structure - Reduces reliance on complex semantic understanding - Creates rich semantic networks for precise information retrieval Lightweight Topology-Enhanced Retrieval - Leverages graph structures for efficient knowledge discovery - Uses pattern matching and localized text processing - Implements query-guided reasoning path discovery Impressive Performance Metrics - Achieves comparable results to LLM-based methods while using Small Language Models (SLMs) - Requires only 25% of storage space compared to existing solutions - Maintains robust performance with accuracy reduction ranging from just 0.8% to 20% The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios. This breakthrough opens new possibilities for: - Edge device AI applications - Privacy-sensitive implementations - Real-time processing systems - Resource-constrained environments The full implementation and datasets are available on GitHub: HKUDS/MiniRAG

liked a Space 2 months ago

fabiochiu/text-to-kb

View all activity

Organizations

None yet

THEFIG's activity

upvoted 4 papers 3 months ago

upvoted 4 collections 4 months ago

CogVideo

Collection

10 items • Updated Feb 12 • 50

UI Agent

Collection

a collection of algorithmic agents for user interfaces/interactions, program synthesis, and robots • 320 items • Updated 1 day ago • 48

Papers

Collection

379 items • Updated 2 days ago • 10

SmolLM2

Collection

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated 26 days ago • 248

upvoted an article 6 months ago

Article

Our Transformers Code Agent beats the GAIA benchmark!

Jul 1, 2024

• 74

upvoted 2 collections 8 months ago

Models Used in HackerNoon Publishing System

Collection

HackerNoon.com’s content management system empowers a small team to manage tens of thousands of writers, advertisers, & millions of readers 🙏 🤖 🙏🤖 • 16 items • Updated Jan 23 • 20

OpenCodeInterpreter

Collection

18 items • Updated Mar 3, 2024 • 84

upvoted a collection 9 months ago

Gemma 2 Release

Collection

15 items • Updated 6 days ago • 216

upvoted a paper 10 months ago

Imp: Highly Capable Large Multimodal Models for Mobile Devices

Paper • 2405.12107 • Published May 20, 2024 • 29

upvoted a collection 12 months ago

OpenCulture

Collection

A multilingual dataset of public domain books and newspapers. • 27 items • Updated Nov 6, 2024 • 124

upvoted 5 papers about 1 year ago

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Paper • 2403.09611 • Published Mar 14, 2024 • 126

Design2Code: How Far Are We From Automating Front-End Engineering?

Paper • 2403.03163 • Published Mar 5, 2024 • 95

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters

Paper • 2403.02677 • Published Mar 5, 2024 • 18

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Paper • 2401.10774 • Published Jan 19, 2024 • 55

BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation

Paper • 2401.17053 • Published Jan 30, 2024 • 32