Sublime

INF-LLaVA Dual-perspective Perception for High-Resolution Multimodal Large Language Model With advancements in data availability and computing resources, Multimodal Large Language Models (MLLMs) have showcased capabilities across various fields. However, the quadratic complexity of the visio... See more

"The TypeScript AI framework." https://t.co/klNjo1U77L

This is an amazingly well written paper, give it a read. Kind of papers you are jealous you are not on the authors' list. @marcgbellemare and the team. https://t.co/j38loSY9FF

Many recent frontier LLMs like Grok-3 and DeepSeek-R1 use a Mixture-of-Experts (MoE) architecture. To understand how it works, let’s pretrain an MoE-based LLM from scratch in PyTorch… nanoMoE is a simple (~500 lines of code) but functional implementation of a mid-sized MoE model that can be pretrained on commodity hardw... See more

Training Trajectories of Language Models Across Scales https://t.co/eElbO6uLv6... See more

MiniMax AI models for text and vision tasks https://t.co/5eckDS9mQe

Multimodal AI model with Vision Transformer and LLM https://t.co/5HHKZ0lAE4