MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Anaerobic digestion (AD) requires close monitoring of key process variables, including pH, the ratio of volatile organic acids to alkaline buffer capacity and biogas production, to maintain…
Efforts to monitor advanced AI for rare misalignments face a data challenge: abundant aligned examples but only a handful of misaligned ones. We test activation probes in this "few vs.
Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer. They are offered off the…
Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is…
End-of-turn (EoT) detection has been studied mostly through features, models, and modalities, while the speech genre of the training data has drawn far less attention. We isolate this factor.
We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstracting from its particular…
Bank-World is a benchmark of 50 banking tasks across two simulated institutions. Completing banking work requires more than producing the right calculation: agents must reconcile records, obtain…
While universal approximation theorems theoretically underpin the representation capabilities of machine learning models, they have two shortcomings: They do not focus on efficient representations…
An uncertainty estimate is meaningful only if its semantics can be tied to observable predictive behavior. Normal-Inverse-Gamma (NIG) evidential regression provides a structured decomposition of…
Zero-shot anomaly detection aims to transfer anomaly discrimination from auxiliary training domains to unseen categories while localizing subtle defects. A key challenge is to construct…
Video world models generate future visual observations from camera or action inputs, with the goal of synthesizing persistent 3D worlds that can be explored across time and space. Existing benchmarks…
Modern machine learning models are often overparameterized, i.e., have more parameters than training data. This typically implies that the loss function admits multiple minimizers so that training…
AdaGrad-style methods can simultaneously adapt to both the order and constants of smoothness in centralized optimization. However, existing extensions to federated optimization with heterogeneous…
Accurate oriented detection requires a box to follow object boundaries, yet a standard regression head predicts its center, size, and angle from a pooled region representation. Small errors in these…
Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but…
Agentic reinforcement learning (RL) often requires repeated tool calls in task-specific environments. A training job may create thousands of these environments in bursts while sharing a cluster with…
Adaptive inference systems balance accuracy and inference cost by routing inputs to models with varying capabilities. Although jointly training models and routers is empirically more sample-efficient…
Localization is an essential capability of intelligent robots. However, in real-world constrained environments, robots often cannot rely on external localization systems.
Video-based gait assessment often keeps only high-confidence pose observations, which can lower measurement error but change the movement assessed. We compared confidence selection with…
Iterative refinement models have significantly improved stereo matching accuracy, but their rigid, fixed update schedules incur heavy computational costs and a strict trade-off between speed and…
Smartphone indoor localization requires low-cost, robust positioning across scene transitions and phone-use variations. Pedestrian dead reckoning (PDR) enables infrastructure-free deployment but…
Artificial intelligence for science (AI4S) is extending from interpretation of existing data to the design and execution of experiments. Space offers distinctive scientific opportunities while…
Hardware-accelerated spiking neural networks (SNNs) implemented on memristive crossbar arrays offer significant gains in energy efficiency, while device variability and analog noise are sometimes…
We introduce machine learning models that accurately predict the electron density, the central variable of density functional theory. They are built on Transformer-inspired architectures, which…