Accuracy
Time-Reversal Provides Unsupervised Feedback to LLMs
A recent line of work aims at specially prompting LLMs to review their own generations and generate meaningful natural language feedback, which can subsequently be used to refine them [Madaan et al.,
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection Ying Y ang
Code is available at https://github.com/xbyym/DLSR. If the test data does not follow the training distribution, the model could unintentionally produce nonsensical predictions, resulting in some misleading conclusions.
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement Zhehao Huang, Xinwen Cheng, JingHao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang Shanghai Jiao Tong University
However, computing the second-order Hessian for large-scale models is intractable.
Faster Repeated Evasion Attacks in Tree Ensembles
Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, i.e., slightly perturbed examples that
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
Kernel ridge regression (KRR) is a central tool in machine learning due to its ability to provide a flexible and efficient framework for capturing intricate patterns within data.
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
Learn-to-Defer is a paradigm that enables learning algorithms to work not in isolation but as a team with human experts.
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
First, we establish that margin consistency is a necessary and sufficient condition to use a model's logit margin as a score for identifying non-robust samples.