Feng Chen
8 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills to improve the interpretability and emotional quality of conversational AI.
The paper proposes ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills to improve the interpretability and emotional quality of conversational AI.
The paper introduces polynomial representations as a quantitative, distribution-aware metric for measuring model simplicity, demonstrating that the effective degree of this representation is a superior predictor of generalization compared to existing proxies.
This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform moderately, there is significant room for improvement in handling complex financial multimodal tasks.
The paper introduces polynomial representations as a quantitative, distribution-aware metric for measuring model simplicity, demonstrating that the effective degree of this representation is a superior predictor of generalization compared to existing proxies.
This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform moderately, there is significant room for improvement in handling complex financial multimodal tasks.
This paper develops a theory and optimal solution for the 'network pearls climb stairs' game on graphs.
The paper introduces DexVerse, a large-scale and modular benchmark for dexterous manipulation with 100 tasks, 3 robot arms, 6 hands, and configurable visual variations.
Papers
DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation
Yunchao Yao, Zhuxiu Xu, Tianqi Zhang, Zixian Liu +11 more
The paper introduces DexVerse, a large-scale and modular benchmark for dexterous manipulation with 100 tasks, 3 robot arms, 6 hands, and configurable visual variations.