Technology
Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models Qiong Wu12, Wei Y u
In this paper, we aim at parameter and computation efficient transfer learning (PCETL) for VLP models.
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
To address this issue, multi-domain joint training ( i.e., multi-dataset joint training) should be introduced into point cloud based 3D object detection, to allow 3D detectors to learn from point clouds of
Y otam Alexander *, Nimrod De La Vega
The question of what makes a data distribution suitable for deep learning is a fundamental open problem.
GT A: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
Offline Reinforcement Learning (Offline RL) presents challenges of learning effective decision-making policies from static datasets without any online interactions.
Exploring Diverse In-Context Configurations for Image Captioning Xu Y ang
Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, i .