Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
Paper • 2604.03179 • Published • 1
David Zhang
davidZgw
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models authored a paper 1 day ago
FlexVAR: Flexible Visual Autoregressive Modeling without Residual
Prediction authored a paper 1 day ago
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a
Pre-trained ModelOrganizations
None yet