Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often
lets those tasks learn better jointly. Multi-tasking models have become successful and often …

In this paper, we explore the advantages of utilizing transformer structures for addressing
multi-task learning (MTL). Specifically, we demonstrate that models with transformer …

We introduce the first multitasking vision transformer adapters that learn generalizable task
affinities which can be applied to novel tasks and domains. Integrated into an off-the-shelf …

Recently, indiscernible scene understanding has attracted a lot of attention in the vision
community. We further advance the frontier of this field by systematically studying a new …

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can
be applied to a set of different tasks. Sharing parameters allows us to take advantage of the …

Diffusion-based generative models have achieved remarkable success in various domains.
It trains a shared model on denoising tasks that encompass different noise levels …

We propose a unified look at jointly learning multiple vision tasks and visual domains
through universal representations, a single deep neural network. Learning multiple …

Action recognition models have achieved impressive results by incorporating scene-level
annotations, such as objects, their relations, 3D structure, and more. However, obtaining …

Task-conditional architecture offers advantage in parameter efficiency but falls short in
performance compared to state-of-the-art multi-decoder methods. How to trade off …

Diffusion models generate highly realistic images through learning a multi-step denoising
process, naturally embodying the principles of multi-task learning (MTL). Despite the …