Related papers: Eureka-Moments in Transformers: Multi-Step Tasks R…

The level of challenge in stroke rehabilitation has to be carefully chosen to keep the patient engaged and motivated while not frustrating them. This paper presents a simulation where this level of challenge is automatically optimized using…

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer…

Machine learning, artificial intelligence and especially deep learning based approaches are often used to simplify or eliminate the burden of programming industrial robots. Using these approaches robots inherently learn a skill instead of…

Transformer model has gained prominence as a popular deep neural network architecture for neural language processing (NLP) and computer vision (CV) applications. However, the extensive use of nonlinear operations, like softmax, poses a…

When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones. Using a small memory…

Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models' tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction…

Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task…

The field of Natural Language Processing has experienced a dramatic leap in capabilities with the recent introduction of huge Language Models. Despite this success, natural language problems that involve several compounded steps are still…

Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…

Transformers have demonstrated exceptional performance across a wide range of domains. While their ability to perform reinforcement learning in-context has been established both theoretically and empirically, their behavior in…

In recent years, interest in vision-language tasks has grown, especially those involving chart interactions. These tasks are inherently multimodal, requiring models to process chart images, accompanying text, underlying data tables, and…

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

While there have been significant advances in de-tecting emotions in text, in the field of utter-ance-level emotion recognition (ULER), there are still many problems to be solved. In this paper, we address some challenges in ULER in dialog…

Motivated by concerns that AI-driven entry-level automation may deprive new generations of valuable work experience, this paper studies how technological change affects the intergenerational transmission of tacit knowledge -- practical,…

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive…

Regularization and transfer learning are two popular techniques to enhance generalization on unseen data, which is a fundamental problem of machine learning. Regularization techniques are versatile, as they are task- and…

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may similarly outperform current hand-designed optimizers, especially…

Softmax is the de facto standard in modern neural networks for language processing when it comes to normalizing logits. However, by producing a dense probability distribution each token in the vocabulary has a nonzero chance of being…

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…