This work investigates a mechanism for topology-altering geometric behavior induced by angular group actions within the framework of the Alpha Group, demonstrating that a systematic angular sweep can drive spontaneous transitions between Riemannian-like and sub-Riemannian regimes. Motivated by the group-theoretic foundations of geometry established by the Göttingen school and by the central role of invariants in topology, we introduce a setting in which geometric organization emerges from the interplay between an invariant, idempotent operator µ and an angular […]

Ver mais

arXiv:2601.15397v1 Announce Type: new Abstract: The rapid emergence of new entities — driven by cultural shifts, evolving trends, and personalized user data — poses a significant challenge for existing Speech Large Language Models (Speech LLMs). While these models excel at general conversational tasks, their static training knowledge limits their ability to recognize domain-specific terms such as contact names, playlists, or technical jargon. Existing solutions primarily rely on prompting, which suffers from poor scalability: as the entity list grows, […]

Ver mais

arXiv:2601.02535v1 Announce Type: new Abstract: Selecting a single high-quality output from multiple stochastic generations remains a fundamental challenge for large language models (LLMs), particularly in open-ended tasks where no canonical answer exists. While Best-of-N and self-consistency methods show that aggregating multiple generations can improve performance, existing approaches typically rely on external evaluators, reward models, or exact string-match voting, limiting their applicability and efficiency. We propose Mode Extraction (ModeX), an evaluator-free Best-of-N selection framework that generalizes majority voting to […]

Ver mais

arXiv:2602.05970v1 Announce Type: cross Abstract: Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width may contribute to performance differently, requiring more detailed studies. Here, we quantify how depth affects loss via analysis of LLMs and toy residual networks. We find loss scales inversely proportional to depth in LLMs, probably due to functionally similar layers reducing error through ensemble averaging rather than compositional learning or discretizing smooth dynamics. This regime is […]

Ver mais

Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon by analyzing how the sampling policy’s coverage evolves throughout on-policy training. We propose and rigorously justify the emph{coverage improvement principle}: with sufficient batch size, each update moves into a region around the target where coverage is uniformly better, making subsequent data increasingly informative and enabling rapid convergence. In […]

Ver mais

Reliable agentic AI requires not only accurate reasoning and adaptive control, but also mechanisms that preserve reliability over time. While recent work has introduced system-level evaluation frameworks (e.g., HB-Eval) and real-time control architectures (e.g., Adapt-Plan), the question of how reliability is retained across an agent’s operational lifespan remains largely unaddressed. Existing memory mechanisms typically store experiences based on recency or salience, inadvertently allowing low-quality behaviors to accumulate and degrade long-term performance.This paper introduces Evaluation-Driven Memory (EDM), a persistence […]

Ver mais

The life of a prescription at Amazon Pharmacy From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money. Conversational AI Alexandre Alves Anita Vila September 30, 01:32 PM October 02, 11:42 AM Pharmacies play a vital role in ensuring patients health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial […]

Ver mais

arXiv:2601.08987v1 Announce Type: new Abstract: This work introduces ABE-VVS, a framework that performs attribute based selective coordinate encryption for point cloud based volumetric video streaming, enabling lightweight yet effective digital rights management (DRM). Rather than encrypting entire point cloud frames, our approach encrypts only selected subsets of coordinates ($X, Y, Z$, or combinations), lowering computational overhead and latency while still producing strong visual distortion that prevents meaningful unauthorized viewing. Our experiments show that encrypting only the $X$ coordinates […]

Ver mais