Archives AI News

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty

arXiv:2509.23002v1 Announce Type: new Abstract: Deploying black-box LLMs requires managing uncertainty in the absence of token-level probability or true labels. We propose introducing an unsupervised conformal inference framework for generation, which integrates: generative models, incorporating: (i) an LLM-compatible atypical score…

Sobolev norm inconsistency of kernel interpolation

arXiv:2504.20617v2 Announce Type: replace Abstract: We study the consistency of minimum-norm interpolation in reproducing kernel Hilbert spaces corresponding to bounded kernels. Our main result give lower bounds for the generalization error of the kernel interpolation measured in a continuous scale…

Functional Complexity-adaptive Temporal Tensor Decomposition

arXiv:2502.06164v3 Announce Type: replace-cross Abstract: Tensor decomposition is a fundamental tool for analyzing multi-dimensional data by learning low-rank factors to represent high-order interactions. While recent works on temporal tensor decomposition have made significant progress by incorporating continuous timestamps in latent…

Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures

arXiv:2412.06655v3 Announce Type: replace-cross Abstract: Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic reward function…

$textit{New News}$: System-2 Fine-tuning for Robust Integration of New Knowledge

arXiv:2505.01812v2 Announce Type: replace-cross Abstract: Humans and intelligent animals can internalize new information and accurately internalize their implications to perform downstream tasks. While large language models (LLMs) can achieve this through in-context learning (ICL) when the information (news) is explicitly…

Analysis of Variational Autoencoders

arXiv:2509.22994v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational methods into SAE architectures can improve feature organization…

Nirvana AI Governance: How AI Policymaking Is Committing Three Old Fallacies

arXiv:2501.10384v2 Announce Type: replace-cross Abstract: This research applies Harold Demsetz’s concept of the nirvana approach to the realm of AI governance and debunks three common fallacies in various AI policy proposals–“the grass is always greener on the other side,” “free…