Deep Learning
Dino/Dino v2 explained: Self-distillation with no labels & etc. #FYI #Tips #Explained #Tutorial 1. https://medium.com/@anuj.dutt9/emerging-properties-in-self-supervised-vision-transformers-dino-paper-summary-4c7a6ed68161 Original Dino 2. https://encord.com/blog/dinov2…
https://www.samarkhanna.com/ExPLoRA/ Parameter-Efficient Extended Pre-training to Adapt Vision Transformers under Domain Shifts
#Paper #Framework
#Paper #Framework
Samarkhanna
ExPLoRA
ExPLoRA: Parameter-Efficient Extended Pre-training to Adapt Vision Transformers under Domain Shifts
https://medium.com/version-1/the-rise-of-large-action-models-lams-how-ai-can-understand-and-execute-human-intentions-f59c8e78bc09
Large Action Models
Large Action Models
Medium
The Rise of Large Action Models, LAMs: How AI Can Understand and Execute Human Intentions?
A hot topic and development in the realm artificial intelligence (AI) is Large Action Models, also referred as Large Agentic Models or LAMs…
https://arxiv.org/pdf/2411.07975
JanusFlow: Harmonizing Autoregression and Rectified Flow
for Unified Multimodal Understanding and Generation
#Paper
Finally multimodality on input and output!
JanusFlow: Harmonizing Autoregression and Rectified Flow
for Unified Multimodal Understanding and Generation
#Paper
Finally multimodality on input and output!
https://github.com/trent-b/iterative-stratification scikit-learn compatible cross validators and splitting with stratification for multilabel data. #library
GitHub
GitHub - trent-b/iterative-stratification: scikit-learn cross validators for iterative stratification of multilabel data
scikit-learn cross validators for iterative stratification of multilabel data - trent-b/iterative-stratification
https://paperswithcode.com/methods/category/convolutions
Known types of convolutions, including deformable convolutions and the latest PushPull-Conv
Known types of convolutions, including deformable convolutions and the latest PushPull-Conv
Paperswithcode
Papers with Code - An Overview of Convolutions
Convolutions are a type of operation that can be used to learn representations from images. They involve a learnable kernel sliding over the image and performing element-wise multiplication with the input. The specification allows for parameter sharing and…
https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL
https://github.com/XiaomiMiMo/MiMo-VL
New Vision Language Model(VLM) that outperforms Qwen2.5-VL #models #vlm
https://github.com/XiaomiMiMo/MiMo-VL
New Vision Language Model(VLM) that outperforms Qwen2.5-VL #models #vlm
huggingface.co
XiaomiMiMo/MiMo-VL-7B-RL · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Relatively new python tools:
https://docs.astral.sh/uv/ An extremely fast Python package and project manager, written in Rust
https://docs.marimo.io/ marimo is a reactive Python notebook
#Tools
https://docs.astral.sh/uv/ An extremely fast Python package and project manager, written in Rust
https://docs.marimo.io/ marimo is a reactive Python notebook
#Tools
docs.astral.sh
uv
uv is an extremely fast Python package and project manager, written in Rust.
🔥1
Deep Learning
https://github.com/parthsarthi03/raptor #Frameworks
https://github.com/illuin-tech/colpali
Efficient Document Retrieval with Vision Language Models #Frameworks #Models
Efficient Document Retrieval with Vision Language Models #Frameworks #Models
GitHub
GitHub - illuin-tech/colpali: The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol. - illuin-tech/colpali
https://arxiv.org/abs/2506.01928 #Paper
Esoteric Language Models ;)
a new family of models that fuses autoregressive and Masked Diffusion Models paradigms
Esoteric Language Models ;)
a new family of models that fuses autoregressive and Masked Diffusion Models paradigms
arXiv.org
Esoteric Language Models
Diffusion-based language models offer a compelling alternative to autoregressive (AR) models by enabling parallel and controllable generation. Among this family of models, Masked Diffusion Models...