Related papers: SMART: Self-supervised Multi-task pretrAining with…

Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few-shot settings. So pre-trained prompt tuning (PPT) is…

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…

Transformers have gained popularity in the software engineering (SE) literature. These deep learning models are usually pre-trained through a self-supervised objective, meant to provide the model with basic knowledge about a language of…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

In this work, we present a general framework for continual learning of sequentially arrived tasks with the use of pre-training, which has emerged as a promising direction for artificial intelligence systems to accommodate real-world…

While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates that models…

The pre-training of visual representations has enhanced the efficiency of robot learning. Due to the lack of large-scale in-domain robotic datasets, prior works utilize in-the-wild human videos to pre-train robotic visual representation.…

The growing number of pretrained models in Machine Learning (ML) presents significant challenges for practitioners. Given a new dataset, they need to determine the most suitable deep learning (DL) pipeline, consisting of the pretrained…

Self-supervised pretraining has been observed to be effective at improving feature representations for transfer learning, leveraging large amounts of unlabelled data. This review summarizes recent research into its usage in X-ray, computed…

Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical…

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a large number of…

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

We introduce SPECTRE, a fully transformer-based foundation model for volumetric computed tomography (CT). Our Self-Supervised & Cross-Modal Pretraining for CT Representation Extraction (SPECTRE) approach utilizes scalable 3D Vision…

Amos et al. (2024) showed that the accuracy of Transformer models in sequence classification can be significantly improved by first pretraining with a masked token prediction objective without external data or augmentation, a procedure…

The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in Reinforcement…

Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. However, the scarcity of large-scale driving datasets has hindered the development…

In this work, we introduce SMART-LLM, an innovative framework designed for embodied multi-robot task planning. SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models (LLMs), harnesses the power of LLMs to convert…

In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly selected small training…