arxiv:2503.21696
Wenqi Zhang
zwq2018
AI & ML interests
LLM, Multimodal, Robotics
Recent Activity
submitted a paper about 20 hours ago
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification upvoted a paper about 21 hours ago
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification upvoted a paper 1 day ago
PersonaVLM: Long-Term Personalized Multimodal LLMs