GitHub

Outlier-Safe Pre-Training

Quantization plays a crucial role in deploying Large Language Models (LLMs) in resource-constrained environments. However, the presence of outlier features significantly hinders low-bit quantization.
IEEE

Adaptive Encoder-Decoder Model Considering Spatio-Temporal Features for Short-Term Power Prediction of Distributed Photovoltaic Station

Abstract: Considering the impact of operation and maintenance costs and technology, there is generally a lack of sufficient meteorological observation devices within the distributed photovoltaic (PV) ...
GitHub

Time Series Foundation Model - TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

The official code for ["TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)"]. TEMPO is one of the very first open source Time Series Foundation Models for ...
ndtvprofit

Centre Pre-Publishes Draft Rules On Four Labour Codes To Seek Stakeholders' Feedback

The Ministry of Labour and Employment on Wednesday pre-published draft rules on the four labour codes on wages, industrial relation, social security and safety, health and working conditions to seek ...
IEEE

Code at the Receiver, Decode at the Sender: GRAND with Feedback

Abstract: In a setting where the forward and feedback channel are noisy BSCs, we show how capacity is nearly achievable in a scheme with only source coding on the forward channel. In representative ...