2 papers
cs.LG2026
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
Yifan Zhang, Yuxin Hu, Zhuobin Hao +2
Self-paced learning (SPL) is an effective learning paradigm that simulates the human learning process by progressing from easy to difficult samples based on the value of the loss f…
cs.AI2026
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
Zhengbo Jiao, Yiming Cheng, Yilei Jiang +15
Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search…