Restez à la pointe de la tech

Intelligence Artificielle

Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute

arXiv:2610.10845v1 Announce Type: new Abstract: A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every time the prompt is sent. We test a memory layer, the public package galahad-kv, that saves the KV state of each block of about 16,000 tokens to encrypted local NVMe disk and loads…

Lire l'article

Intelligence Artificielle

Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models

arXiv:2610.10827v1 Announce Type: new Abstract: Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate into an actionable view of grammar mastery. Prompted frontier models can provide such a view from learner--tutor lesson transcripts, but they are costly at scale. We close this gap by…

Lire l'article

Intelligence Artificielle

Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale

arXiv:2610.10758v1 Announce Type: new Abstract: Enterprise conversation analytics asks many questions of millions of interactions. Each question can require reconstructing what people mean and identifying which information matters, repeating costly interpretive work across the same transcripts. We propose a simple principle: clarify the text, then focus the reader. Statement…

Lire l'article

Intelligence Artificielle

Lossy Compressive Text Autoencoders

arXiv:2610.10738v1 Announce Type: new Abstract: Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning. We propose an autoencoder architecture that performs residual downscaling and upscaling of hidden representations along the time axis, with a residual low-dimension discrete bottleneck. We…

Lire l'article

Intelligence Artificielle

Cognitive Thermometers: Machine Learning and Logical Complexity

arXiv:2610.10724v1 Announce Type: new Abstract: How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on logical definability and complexity, but these are highly sensitive to the choice of logical language, rendering some design choices unmotivated. In this article, we propose that…

Lire l'article

Intelligence Artificielle

Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System

arXiv:2610.10650v1 Announce Type: new Abstract: Work zones are critical yet hazardous components of transportation infrastructure, requiring carefully designed Transportation Management Plans (TMPs) to ensure safety and mobility. However, TMP preparation remains labor-intensive and heavily dependent on practitioner expertise. This paper proposes a Large Language Model…

Lire l'article