Event – AI HKUST(GZ)

All Events

AI Thrust Continouisly Provides Seminars to Share Our Best

Advanced Technologies and Applications of Deep Reinforcement Learning

Deep Model Fusion: Methods and Applications

Towards Transparent Deep Representation Learning

Analysis and Research on Trustworthy LLMs

Efficient and Multi-modal Agent with Large Language Models

Machine Consciousness – Challenges and Possibilities 机器意识：挑战与可能性

Advancing Self-supervised Audio Learning and Its Integration with Large Language Models

OCR Foundation Models: Current Status and Future Prospects 关于OCR大模型的一些思考

Knowledge Intelligence Driven Reliable Recommendation Algorithms

Assistive Hearing Technology: Innovations From Psychoacoustics to Brain-computer Interface

DETR and Beyond: Advancing Open-Set Object Detection with Language and Visual Prompts

Graph Machine Learning: Theory, Technology and Applications

Transferability Guided Transfer Learning

LLM meets Reinforcement Learning (AIAA6102)

Building the Singing Voice Foundation Model (AIAA6101)

点云增强解析技术及其应用研究

Advancements in Computational Creativity: Investigation on 3D Generation and LLM agent society

From LLM to LMM: The Key Role of Massive Scale Dataset for Human Motion | 从LLM到LMM：超大规模人类动作数据集的关键影响

AGI 变革与产业实践

Generative Reasoning in Pretrained Language Models

Deploying Intelligent Autonomy at a Large Scale – Generalizability, Safety, Embodiment

Automatic Captioning of Open Visual World

Facial Representation Learning & its Applications in Facial Editing

Physics-informed Scientific Computing

Large Language Model (LLM) in Autonomous Driving

Online Ensemble: A Theoretical Framework for Non-stationary Online Learning

Knowledge-driven AI and Think-on-Graph

Pretrained Models, Alignment Tech and Agents

Planting a Seed of Vision in Large Language Model

An Introduction to Balanced Multimodal Learning

On Robustness of Vision Models in the 3D World

Learning Universal Representations Across Tasks and Domains

Towards Efficient Video Understanding

The Rise of Vision-Language Foundation Models: Methods, Evaluation and Applications

RHOS: Robot, Human, Object, and Scene

Recent Progress of Generative AI in HUAWEI Noah’s Ark Lab

Developing an Internet and Blockchain Emulator for Reseach and Education

Cross-modal Pretraining for Open-set Detection and Segmentation

Modeling Visual Data Structures for Semantic Segmentation

Searchable Symmetric Encryption and its Attacks

Enhanced 3D Point Cloud Analysis and its Applications

AI-driven 3D Content Generation & Reconstruction for Intelligent Systems

ChatGPT惊艳：人工智能对人类未来的”危与机”

数据驱动的人工智能研究青年学者交流论坛

Data is Urgent to 3D Research Community

Meta-Learning for Complex Tasks

Machine Learning in Model Predictive Control

Translating Across Modalities: Innovations in Visual-to-Text and Text-to-Visual Generation

Developing Interpretable Temporal Point Process Models for Healthcare

Harnessing Vibrations for Finger Interactions with Commodity Smartwatches