Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

A curated list of early exiting (LLM, CV, NLP, etc)

Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)

(NeurIPS-2019 MicroNet Challenge - 3rd Winner) Open source code for "SIPA: A simple framework for efficient networks"

Code for paper "TLEE: Temporal-wise and Layer-wise Early Exiting Network for Efficient Video Recognition on Edge Devices"

Code for paper "Joint Adaptive Resolution Selection and Conditional Early Exiting for Efficient Video Recognition on Edge Devices"

Improve a Model's accuracy by distilling knowledge to the earlier layers of the model. Improves accuracy and performance of lightweight DNN models

Official repository of Busolin et al., "Learning Early Exit Strategies for Additive Ranking Ensembles", ACM SIGIR 2021.

Repository for Novel Early Exiting Methodology for tensorflow deep learning models.

This repository contains the program used to train and evaluate a Branched DNN capable of early-exit semantic segmentation, suited for an edge-cloud co-inference scenario in smart cities..

Lightweight PyTorch implementation of Mixture-of-Recursions with Expert-Choice & Token-Choice routing | Runs on your laptop!

This repository contains some simple experiments revolving around early-exiting