DLISh is a ground level system which facilitates the storage and sharing of information on, and between, blockchains.

Multivariate Temporal Response Function

This is a python script which read a file you pass and then convert it to an equivalent encryption algorithm you choose. The program also can decrypt the encrypted file without any mention of algorithm used during encryption.

[ACL 2022] Transformers for Input Method Engine

[ICASSP20] A Dialogical Emotion Decoder For Speech Emotion Recognition in Spoken Dialog

A CRC-aided successive cancellation list (SCL) decoding algorithm for polar codes and PAC codes with various code constructions/rate profiles. The list decoding algorithm is an adaptive two stage successive cancellation list (SCL) algorithm. First it tries L=1 and then L=L_max. The performance is the same is list decoding with L_max.

An end-to-end solution on how MCQs can be generated using T5 transformer model, word embeddings and decoding strategies

In DSSS with the help of as certain special code we are going to enocoding the data from sender's side and to get the data safely at the receiver end, we have to decode it with the help of special code provided by sender.

C implementation of Huffman coding algorithm.

Source code for brain data processing and analysis in paper <A controller-peripheral architecture and costly energy principle for learning>

A MATLAB function library containing encoders, decoders and weight enumerators for Reed-Muller codes.

JSfuck and hieroglyphy Decoder and ENCODER

素体上の古典的Goppa符号をピーターソン復号したもの。

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"

Viterbi decoder with vectorisation written in C++

awesome-LLM-controlled-constrained-generation

This project implements a decoding algorithm using MCMC (Markov Chain Monte Carlo) methods in R. The approach leverages probabilistic sampling to estimate hidden states in a sequence, commonly used in applications like hidden Markov models and Bayesian inference. The code includes data preprocessing, model setup, and result.

[EMNLP 2024 Findings] Official PyTorch Implementation of "Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation"

Study Physical Layer Authentication in a Bluetooth channel by implementing an effective decoding algorithm able to classify messages as legitimate or non legitimate