collaborators

6 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

Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS

Liangwei Nathan Zheng, Wenhao Liang, Wei Emma Zhang +3

Pseudo-Alignment is a pervasive challenge in many large language models for time series (LLM4TS) models, often causing them to underperform compared to linear models or randomly in…

cs.LG2025

Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers

Wenhao Liang, Chang Dong, Liangwei Zheng +2

Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration Loss (FCL), which adds a squared prob…

eess.IV2025

We Care Each Pixel: Calibrating on Medical Segmentation Model

Wenhao Liang, Wei Zhang, Lin Yue +3

Medical image segmentation is fundamental for computer-aided diagnostics, providing accurate delineation of anatomical structures and pathological regions. While common metrics suc…

cs.LG2025

PostHoc FREE Calibrating on Kolmogorov Arnold Networks

Wenhao Liang, Wei Emma Zhang, Lin Yue +3

Kolmogorov Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov Arnold representation theorem that leverage B Spline parameterizations for flexible, locally a…