ArXiv TLDR

Xiaobai Li

2 papers · Latest:

Human-Computer Interaction

AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition

AffectGPT-RL uses reinforcement learning to optimize non-differentiable metrics in open-vocabulary multimodal emotion recognition, achieving SOTA results.

2605.06126
Computer Vision

GAViD: A Large-Scale Multimodal Dataset for Context-Aware Group Affect Recognition from Videos

GAViD is a new large-scale multimodal dataset with 5091 videos and a novel CAGNet model for context-aware group affect recognition.

2604.16214

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.