arXiv:2601.15324v1 Announce Type: new Abstract: Adding memory to pretrained language models typically requires architectural changes or weight modification. We present Prometheus Mind, which retrofits memory to a frozen Qwen3-4B using 11 modular adapters (530MB, 7% overhead) — fully reversible by removing the adapters. Building this system required solving four problems: (1) Extraction — we develop Contrastive Direction Discovery (CDD), which finds semantic directions via minimal pairs without labeled data. (2) Training — end-to-end optimization collapses; stage-wise training of […]

Ver mais

arXiv:2603.23515v1 Announce Type: new Abstract: Improving the accuracy and reliability of medical coding reduces clinician burnout and supports revenue cycle processes, freeing providers to focus more on patient care. However, automating the assignment of ICD-10-CM and CPT codes from clinical documentation remains a challenge due to heterogeneous records, nuanced coding guidelines, and long-tail distributions. Large language models have been proposed to help or automate specific medical coding tasks. However, foundation models are not explicitly trained for medical coding […]

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:2601.02427v1 Announce Type: new Abstract: We introduce NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. We incorporate three key ingredients: 1) an internet-scale video-action dataset constructed by automatically extracting player actions from publicly available gameplay videos, 2) a multi-game benchmark environment that can measure cross-game generalization, and 3) a unified vision-action model trained with large-scale behavior cloning. NitroGen exhibits strong competence across diverse […]

Ver mais

arXiv:2603.03417v1 Announce Type: new Abstract: Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration. A well-calibrated verifier not only improves answer selection, but also enables early-stopping strategies […]

Ver mais

arXiv:2505.15643v2 Announce Type: replace-cross Abstract: We study best-arm identification in stochastic multi-armed bandits under the fixed-confidence setting, focusing on instances with multiple optimal arms. Unlike prior work that addresses the unknown-number-of-optimal-arms case, we consider the setting where the number of optimal arms is known in advance. We derive a new information-theoretic lower bound on the expected sample complexity that leverages this structural knowledge and is strictly tighter than previous bounds. Building on the Track-and-Stop algorithm, we propose a […]

Ver mais

arXiv:2603.13085v1 Announce Type: cross Abstract: Understanding the theoretical foundations of attention mechanisms remains challenging due to their complex, non-linear dynamics. This work reveals a fundamental trade-off in the learning dynamics of linearized attention. Using a linearized attention mechanism with exact correspondence to a data-dependent Gram-induced kernel, both empirical and theoretical analysis through the Neural Tangent Kernel (NTK) framework shows that linearized attention does not converge to its infinite-width NTK limit, even at large widths. A spectral amplification result […]

Ver mais

Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically given sufficient training data for the desired behavior. Existing LLM-based prompt optimizers attempt this but are ineffective at learning constitutions since (i) they require many labeled examples and (ii) lack structure in the optimized prompts, leading to diminishing improvements as prompt size grows. […]

Ver mais

arXiv:2507.01613v4 Announce Type: replace Abstract: Paired comparison data, where users evaluate items in pairs, play a central role in ranking and preference learning tasks. While ordinal comparison data intuitively offer richer information than binary comparisons, this paper challenges that conventional wisdom. We propose a general parametric framework for modeling ordinal paired comparisons without ties. The model adopts a generalized additive structure, featuring a link function that quantifies the preference difference between two items and a pattern function that […]

Ver mais