Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token level or globally at the sequence level. Therefore, their success depends on a fundamental question: when does sequence probability, that is, the conditional probability of a continuation given a prompt, actually align with correctness? In this paper, we set out to quantify this relationship across decoding methods, models, and benchmarks at four levels: across decoding methods, across hyperparameters within a method, across prompt-answer pairs within a dataset, and across repeated responses to the same prompt. We find that higher sequence probability is often predictive of correctness across prompt-answer pairs within a fixed dataset. However, this relationship does not generally transfer to decoding decisions: increasing sequence probability by changing hyperparameters or methods does not reliably improve accuracy. Further, sequence probability is not a good indicator of correctness for responses to the same prompt. These findings clarify when decoding can and cannot be expected to improve correctness, and provide practical guidance for decoding, self-consistency, and verifier-free self-improvement.

Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power distribution, elicits comparable reasoning without additional training, curated datasets, or verifiers. However, making this method practical requires efficiently sampling from the power distribution. A sampler needs to "mix" to the power distribution, which necessitates moving between modes of the target distribution; intuitively, e.g., trying different reasoning strategies. The samplers proposed in prior works repeatedly select a "cut" position in the current reasoning trace uniformly at random and resample the suffix from that position onward. However, reasoning traces typically contain a few consequential decisions (e.g., the choice of proof strategy or algorithm), and we observe that a uniformly chosen cut tends to rewrite local details rather than revisit decision points. We introduce an algorithm (Entropy-Cut Metropolis-Hastings) that uses the base model's next-token entropy as a proxy to identify key decision points and resample from those positions. We empirically verify that entropy jumps are a useful proxy for decision points and, in a stylized model of reasoning, prove that our method's mixing time scales with the number of decisions in a trace rather than with the number of tokens, which can be much larger. Across MATH500, HumanEval, GPQA Diamond, and AIME26, our method consistently improves over baselines and RL-trained models.

The complex Gaussian distribution has been widely used as a fundamental spectral and noise model in signal processing and communication. However, its Gaussian structure often limits its ability to represent the diverse amplitude characteristics observed in individual source signals. On the other hand, many existing non-Gaussian amplitude distributions derived from hyperspherical models achieve good empirical fit due to their power-law structures, while they do not explicitly account for the complex-plane geometry inherent in complex-valued observations. In this paper, we propose a new probabilistic model for complex-valued random variables, which can be interpreted as a power-weighted noncentral complex Gaussian distribution. Unlike conventional hyperspherical amplitude models, the proposed model is formulated directly on the complex plane and preserves the geometric structure of complex-valued observations while retaining a higher-dimensional interpretation. The model introduces a nonlinear phase diffusion through a single shape parameter, enabling continuous control of the distributional geometry from arc-shaped diffusion along the phase direction to concentration of probability mass toward the origin. We formulate the proposed distribution and analyze the statistical properties of the induced amplitude distribution. The derived amplitude and power distributions provide a unified framework encompassing several widely used distributions in signal modeling, including the Rice, Nakagami, and gamma distributions. Experimental results on speech power spectra demonstrate that the proposed model consistently outperforms conventional distributions in terms of log-likelihood.

Reactor physics is the study of neutron properties, focusing on using models to examine the interactions between neutrons and materials in nuclear reactors. Artificial intelligence (AI) has made significant contributions to reactor physics, e.g., in operational simulations, safety design, real-time monitoring, core management and maintenance. This paper presents a comprehensive review of AI approaches in reactor physics, especially considering the category of Machine Learning (ML), with the aim of describing the application scenarios, frontier topics, unsolved challenges and future research directions. From equation solving and state parameter prediction to nuclear industry applications, this paper provides a step-by-step overview of ML methods applied to steady-state, transient and combustion problems. Most literature works achieve industry-demanded models by enhancing the efficiency of deterministic methods or correcting uncertainty methods, which leads to successful applications. However, research on ML methods in reactor physics is somewhat fragmented, and the ability to generalize models needs to be strengthened. Progress is still possible, especially in addressing theoretical challenges and enhancing industrial applications such as building surrogate models and digital twins.

This paper explains how traditional centralized architectures are transitioning to distributed zonal approaches to address challenges in scalability, reliability, performance, and cost-effectiveness. The role of edge computing and neural networks in enabling sophisticated sensor fusion and decision-making capabilities for autonomous vehicles is examined. Additionally, this paper discusses the impact of zonal architectures on vehicle diagnostics, power distribution, and smart power management systems. Key design considerations for implementing effective zonal architectures are presented, along with an overview of current challenges and future directions. The objective of this paper is to provide a comprehensive understanding of how zonal architectures are shaping the future of automotive technology, particularly in the context of self-driving vehicles and artificial intelligence integration.

Accurately capturing the three dimensional power distribution within a reactor core is vital for ensuring the safe and economical operation of the reactor, compliance with Technical Specifications, and fuel cycle planning (safety, control, and performance evaluation). Offline (that is, during cycle planning and core design), a three dimensional neutronics simulator is used to estimate the reactor's power, moderator, void, and flow distributions, from which margin to thermal limits and fuel exposures can be approximated. Online, this is accomplished with a system of local power range monitors (LPRMs) designed to capture enough neutron flux information to infer the full nodal power distribution. Certain problems with this process, ranging from measurement and calibration to the power adaption process, pose challenges to operators and limit the ability to design reload cores economically (e.g., engineering in insufficient margin or more margin than required). Artificial intelligence (AI) and machine learning (ML) are being used to solve the problems to reduce maintenance costs, improve the accuracy of online local power measurements, and decrease the bias between offline and online power distributions, thereby leading to a greater ability to design safe and economical reload cores. We present ML models trained from two deep neural network (DNN) architectures, SurrogateNet and LPRMNet, that demonstrate a testing error of 1 percent and 3 percent, respectively. Applications of these models can include virtual sensing capability for bypassed or malfunctioning LPRMs, on demand virtual calibration of detectors between successive calibrations, highly accurate nuclear end of life determinations for LPRMs, and reduced bias between measured and predicted power distributions within the core.

Quantum devices need precise control to achieve their full capability. In this work, we address the problem of controlling closed quantum systems, tackling two main issues. First, in practice the control signals are usually subject to unknown classical distortions that could arise from the device fabrication, material properties and/or instruments generating those signals. Second, in most cases modeling the system is very difficult or not even viable due to uncertainties in the relations between some variables and inaccessibility to some measurements inside the system. In this paper, we introduce a general model-free control approach based on deep reinforcement learning (DRL), that can work for any closed quantum system. We train a deep neural network (NN), using the REINFORCE policy gradient algorithm to control the state probability distribution of a closed quantum system as it evolves, and drive it to different target distributions. We present a novel controller architecture that comprises multiple NNs. This enables accommodating as many different target state distributions as desired, without increasing the complexity of the NN or its training process. The used DRL algorithm works whether the control problem can be modeled as a Markov decision process (MDP) or a partially observed MDP. Our method is valid whether the control signals are discrete- or continuous-valued. We verified our method through numerical simulations based on a photonic waveguide array chip. We trained a controller to generate sequences of different target output distributions of the chip with fidelity higher than 99%, where the controller showed superior performance in canceling the classical signal distortions.

The 3D stacking of chips has been the subject of much speculation and innovation in the past decade, and we will be the first to admit that we have been mostly thinking about this as a way to cram more capacity into a given compute engine while at the same time getting components closer together along the Z axis and not just working in 2D anymore down on the X and Y axes. It was extremely interesting to see, then, the 3D wafer-on-wafer stacking that AI chip and system upstart GraphCore has been working on with Taiwan Semiconductor Manufacturing Co had nothing to do making logic circuits more dense within a socket. This will happen over time, of course, but the 3D wafer stacking that GraphCore and TSMC have been exploring together and are delivering in the third generation "Bow" GraphCore IPU – the systems based on them bear the same nickname – is about creating a power delivery die that is bonded to the bottom of the existing compute die. The effect of this innovation is that GraphCore can get a more even power supply to the IPU, and therefore it can drop the voltage on its circuits and therefore increase the clock frequency while at the same time burning less power. The grief and cost of doing this power supply wafer and stacking the IPU wafer on top are outweighed by the performance and thermal benefits on the IPU, and therefore GraphCore and its customers come out ahead on the innovation curve.

Computationally expensive temperature and power grid analyses are required during the design cycle to guide IC design. This paper employs encoder-decoder based generative (EDGe) networks to map these analyses to fast and accurate image-to-image and sequence-to-sequence translation tasks. The network takes a power map as input and outputs the corresponding temperature or IR drop map. We propose two networks: (i) ThermEDGe: a static and dynamic full-chip temperature estimator and (ii) IREDGe: a full-chip static IR drop predictor based on input power, power grid distribution, and power pad distribution patterns. The models are design-independent and must be trained just once for a particular technology and packaging solution. ThermEDGe and IREDGe are demonstrated to rapidly predict the on-chip temperature and IR drop contours in milliseconds (in contrast with commercial tools that require several hours or more) and provide an average error of 0.6% and 0.008% respectively.

Ben Lamm is the CEO and founder of US-based advanced technology solutions provider Hypergiant. The Texan serial entrepreneur--it is his fifth company--embarked on his most ambitious enterprise to-date when he co-founded Hypergiant in 2018. Hypergiant is focused on advanced artificial intelligence (AI) for clients in a wide range of range of sectors from oil drilling and fluid dynamics to entertainment and healthcare. It has an impressive roster of industry partners: consultancies Booz Allen Hamilton and EY; applied science company Dynetics; software companies Adobe, Microsoft, AWS and SAP; and computer hardware company Nvidia. Likewise, its clients include leaders in diverse areas of the oil and gas sector including Shell, US E&P independent Marathon Oil, oilfield services company Schlumberger, conglomerate GE and marketing and trading firm Pacific Summit Energy.