Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]

Anytime Dense Prediction with Confidence Adaptivity (ICLR 2022)

Code for "Fast yet Safe: Early-Exiting with Risk Control" paper

Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions [WACV 2023]

[Arxiv 2024] Official code for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation

[CVPR 2024] Official implement of <Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation>

Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation (CVPR-2024)

[ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

Code for paper "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters" CVPR2024

Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts

The official GitHub page for the survey paper "A Survey on Mixture of Experts".

This package implements THOR: Transformer with Stochastic Experts.

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

Mixture-of-Experts for Large Vision-Language Models

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

pytorch memory track code

Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

[Preprint] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

Source code for "Online Unsupervised Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions", ECCV 2022. This is the code has been implemented to perform training and evaluation of…

Code for "BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation [ICML2024]".

Source code for "To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation", ICCV 2023

A Survey on Continual/Incremental Semantic Segmentation

CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

Code release for "Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation" (NeurIPS 2023)

High-resolution models for human tasks.

Official implementation of "CoMFormer: Continual Learning in Semantic and Panoptic Segmentation"