Related papers: Modular, Hierarchical Machine Learning for Sequent…

This paper investigates robot manipulation based on human instruction with ambiguous requests. The intent is to compensate for imperfect natural language via visual observations. Early symbolic methods, based on manually defined symbols,…

Multi-modal machine learning (ML) models can process data in multiple modalities (e.g., video, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding, activity…

Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However, they generally rely on a separate neural model, specialized and trained for each…

Learning monotonic models with respect to a subset of the inputs is a desirable feature to effectively address the fairness, interpretability, and generalization issues in practice. Existing methods for learning monotonic neural networks…

Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibiting strong instantaneous learning and generalization…

In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones. However, a critical challenge in meta-learning is the task heterogeneity which cannot be…

Open-world machine learning is an emerging technique in artificial intelligence, where conventional machine learning models often follow closed-world assumptions, which can hinder their ability to retain previously learned knowledge for…

As far as Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to the crowd-sourced labeling, and the long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat the…

Code completion, one of the most useful features in the Integrated Development Environments (IDEs), can accelerate software development by suggesting the libraries, APIs, and method names in real-time. Recent studies have shown that…

Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network…

Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and objective criteria are never available at once. The evolution of…

In this work, we aim to establish a strong connection between two significant bodies of machine learning research: continual learning and sequence modeling. That is, we propose to formulate continual learning as a sequence modeling problem,…

Learning new information without forgetting prior knowledge is central to human intelligence. In contrast, neural network models suffer from catastrophic forgetting: a significant degradation in performance on previously learned tasks when…

Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental classification tasks, where models learn to classify new…

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

Computational memory (CM) is a promising approach for accelerating inference on neural networks (NN) by using enhanced memories that, in addition to storing data, allow computations on them. One of the main challenges of this approach is…

Datacenters are increasingly becoming heterogeneous, and are starting to include specialized hardware for networking, video processing, and especially deep learning. To leverage the heterogeneous compute capability of modern datacenters, we…

The merit of ensemble learning lies in having different outputs from many individual models on a single input, i.e., the diversity of the base models. The high quality of diversity can be achieved when each model is specialized to different…

Context. Machine-Learning (ML) solves problems by learning patterns from data, with limited or no human guidance. In Astronomy, it is mainly applied to large observational datasets, e.g. for morphological galaxy classification. Aims. We…

We introduce a new hierarchical deep learning framework for recursive higher-order meta-learning that enables neural networks (NNs) to construct, solve, and generalise across hierarchies of tasks. Central to this approach is a generative…