4 papers
Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations
Xianghao Jiao, Ruoyu Chen, Wei Wang +6
Attribution methods are widely used to characterize the evidence underlying model predictions, yet their potential to improve model behavior remains underexplored. Attribution inco…
Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints
Ruoyu Chen, Shangquan Sun, Xiaoqing Guo +8
Reliable models should not only predict correctly, but also base their decisions on acceptable evidence. However, conventional supervised learning typically provides only class-lev…
Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
Yannan Chen, Ruoyu Chen, Wei Wang +6
Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when thes…
Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation
Ruoyu Chen, Xiaoqing Guo, Kangwei Liu +6
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated token…