Adriel Martins's picture

Adriel Martins

Martins6

·

https://github.com/Martins6

Martins6

AI & ML interests

Graph Neural Networks (GNN) & Robot Learning & Multimodal AI

Recent Activity

liked a model about 22 hours ago

openai/whisper-small

liked a model about 22 hours ago

pyannote/segmentation-3.0

liked a model about 22 hours ago

nvidia/audio-flamingo-3-hf

View all activity

Organizations

None yet

upvoted a collection about 2 months ago

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 21 items • Updated 5 days ago • 114

upvoted an article 5 months ago

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

May 23

• 167

upvoted an article 6 months ago

Article

Vision Language Models (Better, Faster, Stronger)

May 12

• 553

upvoted a paper 7 months ago

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1, 2024 • 172

upvoted 3 collections 8 months ago

DINOv2

DINOv2: foundation models producing robust visual features suitable for image-level and pixel-level visual tasks - https://arxiv.org/abs/2304.07193 • 5 items • Updated Aug 13 • 27

SmolVLM2 📺 Smallest video LM ever 🤏🏻

11 items • Updated May 5 • 99

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5 • 291

upvoted a paper 8 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 152

upvoted a collection 8 months ago

SigLIP2

36 items • Updated Jul 10 • 90

upvoted an article 9 months ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

Feb 4

• 179

upvoted a collection 9 months ago

Phi-3

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 26 items • Updated May 1 • 574

upvoted a paper 9 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 243

upvoted 2 articles 9 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.31k

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 883

upvoted an article 12 months ago

Article

Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU!

By

•

Apr 21, 2024

• 44

upvoted 2 collections about 1 year ago

Open LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 65 items • Updated Mar 20 • 647

LLaVA-Video

Models focus on video understanding (previously known as LLaVA-NeXT-Video). • 8 items • Updated Feb 21 • 63

upvoted a paper about 1 year ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22, 2024 • 133

upvoted 2 papers almost 2 years ago

DocLLM: A layout-aware generative language model for multimodal document understanding

Paper • 2401.00908 • Published Dec 31, 2023 • 188

Improving Text Embeddings with Large Language Models

Paper • 2401.00368 • Published Dec 31, 2023 • 82