🗣 MARS 5 TTS

▪Github: https://github.com/Camb-ai/MARS5-TTS
▪Demo: https://www.camb.ai/
▪HF: https://huggingface.co/CAMB-AI/MARS5-TTS
▪Colab: https://colab.research.google.com/github/Camb-ai/mars5-tts/blob/master/mars5_demo.ipynb

@Machine_learn

🌟 SEE-2-SOUND - a method for generating complex spatial sound based on images and videos

— pip install see2sound

🖥 GitHub
🟡 Hugging Face
🟡 Arxiv

@Machine_learn

Seq2Seq: Sequence-to-Sequence Generator

🖥 Github: https://github.com/fiy2w/mri_seq2seq

📕 Paper: https://arxiv.org/abs/2407.02911v1

🔥Dataset: https://paperswithcode.com/task/contrastive-learning

@Machine_learn

سلام دوستانی که مقاله دارن می تونن به این ژورنال بفرستن و من و به عنوان داور معرفی کنن
@Machine_learn

👁‍🗨 LongVA: Long Context Transfer from Language to Vision

▪Github: https://github.com/EvolvingLMMs-Lab/LongVA
▪Paper: https://arxiv.org/abs/2406.16852
▪Project: https://lmms-lab.github.io/posts/longva/
▪Demo: https://longva-demo.lmms-lab.com/

@Machine_learn

🌟 MG-LLaVA - multimodal LLM with advanced capabilities for working with visual information

Just recently, the guys from Shanghai University rolled out MG-LLaVA - MLLM, which expands the capabilities of processing visual information through the use of additional components: special components that are responsible for working with low and high resolution.

MG-LLaVA integrates an additional high-resolution visual encoder to capture fine details, which are then combined with underlying visual features using the Conv-Gate network.

Trained exclusively on publicly available multimodal data, MG-LLaVA achieves excellent results.

🟡 MG-LLaVA page
🖥 GitHub

@Machine_learn

Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment

🖥 Github: https://github.com/kaistmm/SSLalignment

📕 Paper: https://arxiv.org/abs/2407.13676v1

🚀 Dataset: https://paperswithcode.com/dataset/is3-interactive-synthetic-sound-source

@Machine_learn