Raúl Garrido's picture

113 560

Raúl Garrido

happybydefault

·

https://happybydefault.com

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

microsoft/Phi-4-mini-instruct

liked a model 1 day ago

microsoft/Phi-4-multimodal-instruct

liked a model 2 days ago

microsoft/Magma-8B

View all activity

Organizations

happybydefault's activity

upvoted a paper 3 days ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published 3 days ago • 54

upvoted a collection 3 days ago

olmOCR

olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 3 items • Updated 2 days ago • 49

upvoted an article 7 days ago

Article

SigLIP 2: A better multilingual vision language encoder

8 days ago

• 114

upvoted a collection 7 days ago

SigLIP2

36 items • Updated 8 days ago • 52

upvoted a collection 8 days ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

11 items • Updated 4 days ago • 42

upvoted an article 8 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

9 days ago

• 177

upvoted a collection 9 days ago

PaliGemma 2 Mix

13 items • Updated 9 days ago • 59

upvoted a paper 10 days ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published 13 days ago • 135

upvoted a collection 16 days ago

OLMoE (January 2025)

Improved OLMoE for iOS app. Read more: https://allenai.org/blog/olmoe-app • 10 items • Updated 17 days ago • 9

upvoted a paper 18 days ago

Agency Is Frame-Dependent

Paper • 2502.04403 • Published 23 days ago • 21

upvoted an article 24 days ago

Article

Open-source DeepResearch – Freeing our search agents

25 days ago

• 1.11k

upvoted a paper 25 days ago

MatAnyone: Stable Video Matting with Consistent Memory Propagation

Paper • 2501.14677 • Published Jan 24 • 30

upvoted a paper 28 days ago

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

Paper • 2501.18512 • Published 29 days ago • 27

upvoted a collection 29 days ago

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated 16 days ago • 91

upvoted 6 collections about 1 month ago

POTION

These are the flagship POTION models. Load them and use them with model2vec (https://github.com/MinishLab/model2vec) or sentence-transformers • 5 items • Updated 26 days ago • 10

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated 3 days ago • 102

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 8 items • Updated 5 days ago • 379

DeepSeek-R1-ReDistill

Re-distilled DeepSeek R1 models • 4 items • Updated 30 days ago • 14

GTE ModernBERT

GTE Models Based on ModernBERT • 2 items • Updated Jan 21 • 15

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated Jan 23 • 31