3 papers
cs.AI2025
Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
Jiaqi Wang, Kevin Qinghong Lin, James Cheng +1
Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO)…
cs.LG2025
DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization
Jiaqi Wang, Yuhang Zhou, Zhixiong Zhang +3
Out-of-distribution generalization is a common problem that expects the model to perform well in the different distributions even far from the train data. A popular approach to add…
cs.LG2025
A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs
Jiaqi Wang, Xinyi Wu, James Cheng +1
Deep graph neural networks (GNNs) often suffer from oversmoothing, where node representations become overly homogeneous with increasing depth. While techniques like normalization,…