8 papers · 1 filter
How Accurate Is Accurate Enough?
Ningkang Peng, Qianfeng Yu, Jingyang Mao +2
How accurate must a numerical approximation be within a learning system? Primitive error alone cannot answer this question: errors of the same magnitude can have very different con…
Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?
Ningkang Peng, Qianfeng Yu, Jingyang Mao +4
In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold for high-dimensional distrib…
PIS: A Physics-Informed System for Accurate State Partitioning of Protein Trajectories
Qianfeng Yu, Ningkang Peng, Yanhui Gu
Understanding the conformational evolution of -amyloid (), particularly the isoform, is fundamental to elucidating the pathogenic mechanisms underlying Alzheimer's…
Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion
Ningkang Peng, Kun Shao, Jingyang Mao +4
Deploying trustworthy AI in open-world environments faces a dual challenge: the necessity for robust Out-of-Distribution (OOD) detection to ensure system safety, and the demand for…
Halt the Hallucination: Decoupling Signal and Semantic OOD Detection Based on Cascaded Early Rejection
Ningkang Peng, Chuanjie Cheng, Jingyang Mao +7
Efficient and robust Out-of-Distribution (OOD) detection is paramount for safety-critical applications.However, existing methods still execute full-scale inference on low-level sta…
VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
Ningkang Peng, Qianfeng Yu, Yuhao Zhang +6
Out-of-Distribution (OOD) detection under long-tailed distributions is a highly challenging task because the scarcity of samples in tail classes leads to blurred decision boundarie…
Breaking Semantic Hegemony: Decoupling Principal and Residual Subspaces for Generalized OOD Detection
Ningkang Peng, Xiaoqian Peng, Yuhao Zhang +7
While feature-based post-hoc methods have made significant strides in Out-of-Distribution (OOD) detection, we uncover a counter-intuitive Simplicity Paradox in existing state-of-th…
Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection
Ningkang Peng, JiuTao Zhou, Yuhao Zhang +6
Out-of-distribution (OOD) detection is a critical task for the safe deployment of machine learning models in the real world. Existing prototype-based representation learning method…