arXiv:2601.09028v1 Announce Type: new Abstract: The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented generation (RAG). The quality of generated content heavily relies on the usefulness of the retrieved information and the capacity of LLMs’ internal information processing mechanism to incorporate it in answer generation. It is generally assumed that the retrieved information is relevant to the question. However, the retrieved information may have a variable degree […]

Ver mais

Transformer models have achieved remarkable empirical successes, largely due to their in-context learning capabilities. Inspired by this, we explore training an autoregressive transformer for in-context reinforcement learning (ICRL). In this setting, we initially train a transformer on an offline dataset consisting of trajectories collected from various RL tasks, and then fix and use this transformer to create an action policy for new RL tasks. Notably, we consider the setting where the offline dataset contains trajectories sampled from suboptimal […]

Ver mais

Early AI development relied heavily on scaling neural networks without fully understanding how they worked internally. Researchers are now turning to the spectral properties of linear algebra—particularly eigenvalues and eigenvectors—to better interpret how neural networks process information. By studying the geometry of latent space and identifying meaningful circuits inside transformer models, scientists can isolate and enhance specific capabilities such as reasoning or coding. Hardware innovations are also emerging to accelerate these complex calculations. Ultimately, spectral techniques like normalization […]

Ver mais

I’ve been reviewing how various AI memory systems evaluate their performance and noticed a fundamental issue with cross-system comparison. Most systems benchmark on LOCOMO (Maharana et al., ACL 2024), but the evaluation methods vary significantly. LOCOMO’s official metric (Token-Overlap F1) gives GPT-4 full context 32.1% and human performance 87.9%. However, memory system developers report scores of 60-67% using custom evaluation criteria such as retrieval accuracy or keyword matching rather than the original F1 metric. Since each system measures […]

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:2603.25157v1 Announce Type: cross Abstract: Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond. Despite their empirical success, these architectures remain far from the computational principles of the human brain, often demanding enormous amounts of training data while offering limited interpretability. In this work, we propose the Vision Hopfield Memory Network (V-HMN), a brain-inspired foundation backbone that integrates hierarchical memory […]

Ver mais

arXiv:2604.03939v1 Announce Type: cross Abstract: In many modern applications, a carefully designed primary study provides individual-level data for interpretable modeling, while summary-level external information is available through black-box, efficient, and nonparametric machine-learning predictions. Although summary-level external information has been studied in the data integration literature, there is limited methodology for leveraging external nonparametric machine-learning predictions to improve statistical inference in the primary study. We propose a general empirical-likelihood framework that incorporates external predictions through moment constraints. An advantage […]

Ver mais

The primary focus of multi-agent reinforcement learning (MARL) has been to study interactions among a fixed number of agents embedded in an environment. However, in the real world, the number of agents is neither fixed nor known a priori. Moreover, an agent can decide to create other agents (for example, a cell may divide, or a company may spin off a division). In this paper, we propose a framework that allows agents to create other agents; we call […]

Ver mais