A5003879443- Topic Modeling
- Image Processing and 3D Reconstruction
- Multimodal Machine Learning Applications
- Industrial Vision Systems and Defect Detection
- 3D Shape Modeling and Analysis
- Advanced Neural Network Applications
- 3D Surveying and Cultural Heritage
- Manufacturing Process and Optimization
- Natural Language Processing Techniques
- Visual Attention and Saliency Detection
Hong Kong Polytechnic University
2024
Institute of Automation
2022
University of Chinese Academy of Sciences
2022
The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters. However, closed-source nature state-of-the-art LLMs and their general-purpose training limit role-playing optimization. In this paper, we introduce RoleLLM, a framework benchmark, elicit, enhance abilities in LLMs. RoleLLM comprises four stages: (1) Role Profile Construction 100 roles; (2) Context-Based...
Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance. By performing score distillation sampling (SDS) iteratively across different views, these methods succeed in lifting 2D generative prior to space. However, such a bakes effect illumination and shadow into texture. As result, material maps optimized SDS inevitably involve spurious correlated components. The absence precise definition makes it infeasible...
Existing interactive segmentation methods mainly focus on optimizing user interacting strategies, as well making better use of clicks provided by users. However, the intention model is to obtain high-quality masks with limited interactions, which are supposed be applied unlabeled new images. But most existing overlooked generalization ability their models when witnessing target scenes. To overcome this problem, we propose a life-long evolution framework for in paper, provides possible...