3 papers
cs.CV2026
Probing Routing-Conditional Calibration in Attention-Residual Transformers
Wenhao Liang, Lin Yue, Wei Emma Zhang +4
Post-hoc calibration is usually evaluated as a function of logits or softmax confidence alone, even as routing-augmented architectures increasingly accompany predictions with sampl…
cs.CV2026
Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers
Wenhao Liang, Wei Emma Zhang, Lin Yue +4
Most calibration methods operate at the logit level, implicitly assuming that miscalibration can be corrected without changing the underlying representation. We challenge this assu…
cs.LG2025
Neural Tractability via Structure: Learning-Augmented Algorithms for Graph Combinatorial Optimization
Jialiang Li, Weitong Chen, Mingyu Guo
Neural models have shown promise in solving NP-hard graph combinatorial optimization (CO) problems. Once trained, they offer fast inference and reasonably high-quality solutions fo…