Joao Pedro Silva Dias Moura Mesquita's picture

Joao Pedro Silva Dias Moura Mesquita

inkasaras

·

joaopedrosdmm

AI & ML interests

None yet

Recent Activity

liked a model about 10 hours ago

Qwen/Qwen-Image-Edit

updated a collection about 16 hours ago

liked a model about 16 hours ago

stepfun-ai/Step-Audio-2-mini

View all activity

Organizations

None yet

upvoted a collection 15 days ago

Ovis2.5

Our next-generation MLLMs for native-resolution vision and advanced reasoning • 5 items • Updated 14 days ago • 54

upvoted a collection 17 days ago

HuBERT

A collection of checkpoints from the HuBERT release, a speech encoder that learns powerful representations from unlabelled audio data. • 6 items • Updated Jan 16, 2024 • 7

upvoted 2 collections 18 days ago

Web-SSL

17 items • Updated Apr 23 • 19

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated 11 days ago • 266

upvoted a paper 23 days ago

VeriGUI: Verifiable Long-Chain GUI Dataset

Paper • 2508.04026 • Published 27 days ago • 156

upvoted 2 articles about 1 month ago

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

By

and 4 others •

Jul 29

• 164

Article

Mixture of Experts Explained

By

and 5 others •

Dec 11, 2023

• 862

upvoted 4 papers about 1 month ago

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Paper • 2506.05573 • Published Jun 5 • 78

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents

Paper • 2507.04009 • Published Jul 5 • 41

Yume: An Interactive World Generation Model

Paper • 2507.17744 • Published Jul 23 • 85

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14 • 283

upvoted 2 papers about 2 months ago

Scaling Laws for Optimal Data Mixtures

Paper • 2507.09404 • Published Jul 12 • 35

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published Jul 2 • 61

upvoted an article about 2 months ago

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

By

and 1 other •

Jul 9

• 663

upvoted a collection about 2 months ago

NextCoder

NextCoder family of code-editing LMs developed with Selective Knowledge Transfer and its training data. • 6 items • Updated Jul 9 • 70

upvoted an article 2 months ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

By

and 1 other •

Jul 1

• 113

upvoted a collection 2 months ago

ERNIE 4.5

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 25 items • Updated Jul 11 • 159

upvoted 3 papers 2 months ago

MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation

Paper • 2506.14028 • Published Jun 16 • 93

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Paper • 2506.13585 • Published Jun 16 • 263

WorldVLA: Towards Autoregressive Action World Model

Paper • 2506.21539 • Published Jun 26 • 39