6 papers
CALQA: Conformal Screening of Forecast-Ensemble Configurations from One Mergeable State
Xiufeng Liu, Ruyu Liu, Yusen Liu +2
AutoML systems fit ensemble weights over model libraries; a search can score, per category, market or time pane, thousands of weightings of the quantile-averaged (Vincentized) ense…
HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit
Zhihao Guo, Zonghan Wu, Huan Huo +6
Internal-state probes enable truthfulness prediction before a large language model generates an answer. When detectors change both the layers they read and the rules used to combin…
Causal Discovery with Inverted Self-attention for Multivariate Time Series
Yusen Liu, Yong Wang, Yifan Yin +3
Causal discovery in multivariate time series data is challenging due to complex interactions, high dimensionality, and nonlinear dependencies among variables. Existing methods ofte…
Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives
Xiaolong Liu, Junjian Li, Yuan Xiao +4
Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineerin…
Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
Dayong Ye, Tianqing Zhu, Ruiding Huang +5
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly eras…
Vertical Federated Unlearning via Backdoor Certification
Mengde Han, Tianqing Zhu, Lefeng Zhang +2
Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method…