Novel Attention Mechanisms - a pranay-j Collection

pranay-j 's Collections

Dataset- NLP Reasoning

LLM - Cross Lingual Language Understanding

Novel Attention Mechanisms

LLM_architectures

NLP Parameter Efficient Finetuning

Text to Speech Architectures

Automatic Speech Recognition Architectures

graident optimization

Memory efficient training

Instruction tuning datasets

Language Model Pretraining Dataset

reward model dataset

positional encoding Language models

Domain adaption of dense retrieval

Datasets: For training Embedding Models

audio-language-model-architecture

Novel Attention Mechanisms

updated Feb 18

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

Paper • 2502.11089 • Published Feb 16 • 163