Related papers: REVELIO -- Universal Multimodal Task Load Estimati…
As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…
Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…
Deep learning-based models, when trained in a fully-supervised manner, can be effective in performing complex image analysis tasks, although contingent upon the availability of large labeled datasets. Especially in the medical imaging…
Experience management is an emerging business area where organizations focus on understanding the feedback of customers and employees in order to improve their end-to-end experiences. This results in a unique set of machine learning…
Deep learning based models are used regularly in every applications nowadays. Generally we train a single model on a single task. However, we can train multiple tasks on a single model under multi-task learning settings. This provides us…
Urban and transportation research has long sought to uncover statistically meaningful relationships between key variables and societal outcomes such as road safety, to generate actionable insights that guide the planning, development, and…
Multimodal learning leverages the integration of diverse data modalities to enhance performance in complex tasks. Yet, it frequently encounters incomplete or redundant modality data in real-world scenarios. This paper presents a…
Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this…
The capability of Unified Multimodal Models (UMMs) to apply world knowledge across diverse tasks remains a critical, unresolved challenge. Existing benchmarks fall short, offering only siloed, single-task evaluations with limited diagnostic…
Recent advances in large multimodal models have enabled new opportunities in embodied AI, particularly in robotic manipulation. These models have shown strong potential in generalization and reasoning, but achieving reliable and responsible…
We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple…
Object detection, segmentation and classification are three common tasks in medical image analysis. Multi-task deep learning (MTL) tackles these three tasks jointly, which provides several advantages saving computing time and resources and…
Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…
Multi-Task Learning (MTL) can enhance a classifier's generalization performance by learning multiple related tasks simultaneously. Conventional MTL works under the offline or batch setting, and suffers from expensive training cost and poor…
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in…
As deep learning applications continue to become more diverse, an interesting question arises: Can general problem solving arise from jointly learning several such diverse tasks? To approach this question, deep multi-task learning is…
Cognitive tasks originally developed for humans are now increasingly used to study language models. While applying these tasks is often straightforward, interpreting their results can be challenging. In particular, when a model…
In multi-label learning, a particular case of multi-task learning where a single data point is associated with multiple target labels, it was widely assumed in the literature that, to obtain best accuracy, the dependence among the labels…
Much research in machine learning involves finding appropriate inductive biases (e.g. convolutional neural networks, momentum-based optimizers, transformers) to promote generalization on tasks. However, quantification of the amount of…
Transferability scores aim to quantify how well a model trained on one domain generalizes to a target domain. Despite numerous methods proposed for measuring transferability, their reliability and practical usefulness remain inconclusive,…