arXiv:2511.02022v1 Announce Type: cross Abstract: Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent misalignment (EM). However, the fundamental mechanisms enabling such harmful generalization across disparate domains remain poorly understood. In this work, we adopt a geometric perspective to […]
Watermarking Discrete Diffusion Language Models
arXiv:2511.02083v1 Announce Type: cross Abstract: Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image diffusion models, none address discrete diffusion language models, which are becoming popular due to their high inference throughput. […]
Reliability Assessment Framework Based on Feature Separability for Pathological Cell Image Classification under Prior Bias
arXiv:2511.01953v1 Announce Type: new Abstract: textbfBackground and objective: Prior probability shift between training and deployment datasets challenges deep learning–based medical image classification. Standard correction methods reweight posterior probabilities to adjust prior bias, yet their benefit is inconsistent. We developed a reliability framework identifying when prior correction helps or harms performance in pathological cell image analysis. […]
Apriel-H1: Towards Efficient Enterprise Reasoning Models
arXiv:2511.02651v1 Announce Type: cross Abstract: Large Language Models (LLMs) achieve remarkable reasoning capabilities through transformer architectures with attention mechanisms. However, transformers suffer from quadratic time and memory complexity in the attention module (MHA) and require caching key-value states during inference, which severely limits throughput and scalability. High inference throughput is critical for agentic tasks, long-context […]
Accumulating Context Changes the Beliefs of Language Models
arXiv:2511.01805v2 Announce Type: replace-cross Abstract: Language model (LM) assistants are increasingly used in applications such as brainstorming and research. Improvements in memory and context size have allowed these models to become more autonomous, which has also resulted in more text accumulation in their context windows without explicit user intervention. This comes with a latent risk: […]
Modulation of metastable ensemble dynamics explains the inverted-U relationship between tone discriminability and arousal in auditory cortex
arXiv:2404.03902v3 Announce Type: replace Abstract: Past work has reported inverted-U relationships between arousal and auditory task performance, but the underlying neural network mechanisms remain unclear. To make progress, we recorded auditory cortex activity from behaving mice during passive tone presentation and simultaneously monitored pupil-indexed arousal. In these experiments, neural discriminability of tones was maximized at […]
How Teachers Can Use Large Language Models and Bloom’s Taxonomy to Create Educational Quizzes
arXiv:2401.05914v2 Announce Type: replace-cross Abstract: Question generation (QG) is a natural language processing task with an abundance of potential benefits and use cases in the educational domain. In order for this potential to be realized, QG systems must be designed and validated with pedagogical needs in mind. However, little research has assessed or designed QG […]
LLMs as Layout Designers: Enhanced Spatial Reasoning for Content-Aware Layout Generation
arXiv:2509.16891v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated impressive reasoning and planning abilities in textual domains and can effectively follow instructions for complex tasks, their ability to understand and manipulate spatial relationships remains limited. Such capabilities are crucial for content-aware graphic layout design, where the goal is to arrange heterogeneous elements […]
Autoencoding Random Forests
arXiv:2505.21441v3 Announce Type: replace-cross Abstract: We propose a principled method for autoencoding with random forests. Our strategy builds on foundational results from nonparametric statistics and spectral graph theory to learn a low-dimensional embedding of the model that optimally represents relationships in the data. We provide exact and approximate solutions to the decoding problem via constrained […]
SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization
arXiv:2511.02460v1 Announce Type: cross Abstract: Knowledge graph embedding (KGE) has become a fundamental technique for representation learning on multi-relational data. Many seminal models, such as TransE, operate in an unbounded Euclidean space, which presents inherent limitations in modeling complex relations and can lead to inefficient training. In this paper, we propose Spherical Knowledge Graph Embedding […]