arXiv:2511.20713v1 Announce Type: new Abstract: Large Language Models (LLMs) often exhibit systematic errors on specific subsets of data, known as error slices. For instance, a slice can correspond to a certain demographic, where a model does poorly in identifying toxic…
arXiv:2511.20718v1 Announce Type: new Abstract: PPO has been widely adopted for training large language models (LLMs) at the token level in multi-turn dialogue and reasoning tasks. However, its performance is often unstable and prone to collapse. Through empirical analysis, we…
arXiv:2511.20705v1 Announce Type: new Abstract: Inverse problems are fundamental to science and engineering, where the goal is to infer an underlying signal or state from incomplete or noisy measurements. Recent approaches employ diffusion models as powerful implicit priors for such…
arXiv:2511.20704v1 Announce Type: new Abstract: Early and accurate detection of Alzheimer’s disease (AD) is crucial for enabling timely intervention and improving outcomes. However, developing reliable machine learning (ML) models for AD diagnosis is challenging due to limited labeled data, multi-site…
arXiv:2511.20702v1 Announce Type: new Abstract: Model pruning is a widely adopted technique to reduce the computational complexity and memory footprint of Deep Neural Networks (DNNs). However, global unstructured pruning often leads to significant degradation in accuracy, typically necessitating fine-tuning on…
arXiv:2506.04263v2 Announce Type: replace-cross Abstract: Adversarial training is among the most effective strategies for defending deep neural networks against adversarial examples. A key limitation of existing adversarial training approaches lies in their reliance on a fixed perturbation budget, which fails…
arXiv:2511.20729v1 Announce Type: new Abstract: Foundation models (FMs) have emerged as a powerful paradigm, enabling a diverse range of data analytics and knowledge discovery tasks across scientific fields. Inspired by the success of FMs, particularly large language models, researchers have…
arXiv:2511.20779v1 Announce Type: new Abstract: Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial complement to effectively support human experts during inference. This work proposes the Calibrated…
arXiv:2511.21600v1 Announce Type: cross Abstract: The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and public policy, raising growing concerns about data provenance and misuse. Watermarking offers a promising…
arXiv:2511.20798v1 Announce Type: new Abstract: Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but also distinct, human-understandable abstract concepts and behaviour. Moreover, these hidden features can be…
