Core Tech

  • Posted On:

Data Representation and Learning for Dialogue Sy...

The application of voice assistants is becoming more and more popular, however, due to the inefficiency of artificial intelligence-based technology, current products are mostly built by using rules...

Continue Reading
  • Posted On:

Snippet Policy Network: Knee-Guided Neuroevoluti...

We have proposed in this project the first time series classification technique that considers accuracy, earliness, and varied lengths simultaneously, containing a novel deep reinforcement learning...

Continue Reading
  • Posted On:

Super-fast Convergence for Radiance Fields Recon...

The NeRF-based technique describes a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses.

Continue Reading
  • Posted On:

Deep Reinforcement Learning in Autonomous Minia...

This project develops a high-performance end-to-end reinforcement learning training platform for autonomous miniature car racing. With this platform, our team won the championship of Amazon DeepRac...

Continue Reading
  • Posted On:

A comprehensive evaluation of self-supervised sp...

Machines need annotations to learn, but human babies learn human languages with almost no annotations. Can machines do the same thing? To allow machines to learn human languages with only observati...

Continue Reading
  • Posted On:

YOLOv7

YOLOv7 is a new generation of real-time object detector, which provides the most advanced real-time object detection architecture from edge computing to cloud computing.

Continue Reading
  • Posted On:

Advanced Technologies for Designing Trustable AI...

This integrated research project follows the Taiwan's 2030 Science & Technology Vision and takes LOHAS community and inclusive technology as the major research direction. We aim to develop trustabl...

Continue Reading
  • Posted On:

Embedding multimodal machine intelligence in the...

This project collaborates with the international team to collect a very large-scale Chinese emotional corpus. In terms of technology, the fairness of speech emotion recognition is also discussed to...

Continue Reading
  •  對話系統之資料表示與學習(II)
  •  前瞻性時間序列機器學習核心技術及整合工具之研發
  •  跨模態資料學習於圖像語意理解、描述、生成與操控
  •  Constructing a Novel AI Training Pipeline : From Flexible Annotation Tool to Lifelong Learning
  •  Learning from Cross-Modality Data for Image Semantics Understanding, Description, Synthesis, & Manipulation
  •  Development of Advanced Time Series Machine Learning Core Techniques and Integrated Tools
  •  Data Representation and Learning for Dialogue System (II)