arXiv preprints from January 1, 2026 through September 15, 2026 — 20:19:59 EST
We demonstrate a deep learning framework capable of recovering physical parameters from the Nonlinear Schrodinger Equation (NLSE) under severe noise conditions. By integrating Physics-Informed Neural Networks (PINNs) with automatic differentiation, we achieve reconstruction of the nonlinear coefficient beta with less than 0.2 percent...
Alignment of artificial intelligence (AI) encompasses the normative problem of specifying how AI systems should act and the technical problem of ensuring AI systems comply with those specifications. To date, AI alignment has generally overlooked an important source of knowledge and practice for grappling with these problems: law. In...
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE) agent settings often relies on code execution, which can be difficult to scale due to environment...
Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study introduces the concept of agent drift, defined as the progressive degradation of agent behavior,...
Given a planar graph, a subset of its vertices called terminals, and $k \in \mathbb{N}$, the Face Cover Number problem asks whether the terminals lie on the boundaries of at most $k$ faces of some embedding of the input graph. When a plane graph is given in the input, the problem is known to have a polynomial...
Establishing frameworks for promoting the realization of various activities on celestial bodies sustainably is of great significance for different contexts, such as preserving the scientific evidence and space heritage. Therefore, this research first proposes a conceptual model that covers the different types of features, attributes,...
Grant-free cell-free massive multiple-input multiple-output (GF-CF-MaMIMO) systems are anticipated to be a key enabling technology for next-generation Internet-of-Things (IoT) networks, as they support massive connectivity without explicit scheduling. However, the large amount of connected devices prevents the use of orthogonal pilot...
The application of machine learning on healthcare data is often hindered by the lack of standardized and semantically explicit representation, leading to limited interoperability and reproducibility across datasets and experiments. The Medical Event Data Standard (MEDS) addresses these issues by introducing a minimal, event-centric...
This study presents a unified Attention U-Net architecture trained jointly on MRI (BraTS 2021) and CT (LIDC-IDRI) datasets to investigate the generalizability of a single model across diverse imaging modalities and anatomical sites. Our proposed pipeline incorporates modality-harmonized preprocessing, attention-gated skip connections,...
World models have become central to autonomous driving, where accurate scene understanding and future prediction are crucial for safe control. Recent work has explored using vision-language models (VLMs) for planning, yet existing approaches typically treat perception, prediction, and planning as separate modules. We propose...
Supporting Go/No-Go decisions prior to launch requires assessing real-time telemetry data against redline limits established during the design qualification phase. Family data from ground testing or previous flights is commonly used to detect initiating failure modes and their timing; however, this approach relies heavily on...
Prolonged length of stay (pLoS) is a significant factor associated with the risk of adverse in-hospital events. We develop and explain a predictive model for pLos using admission-level patient and hospital administrative data. The approach includes a feature selection method by selecting non-correlated features with the highest...
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale datasets-often collected from human or web sources-makes them vulnerable to backdoor attacks,...
Machine learning models are increasingly used in high-stakes domains where their predictions can actively shape the environments in which they operate, a phenomenon known as performative prediction. This dynamic, in which the deployment of the model influences the very outcome it seeks to predict, can lead to unintended consequences,...
We show that Inner Product in $2n$ variables, $\mathbf{IP}_n(x, y) = x_1y_1 \oplus \ldots \oplus x_ny_n$, can be computed by depth-3 bottom fan-in 2 circuits of size $\mathsf{poly}(n)\cdot (9/5)^n$, matching the lower bound of Göös, Guan, and Mosnoi (Inform. Comput.'24). Our construction is obtained via the following steps. - We...
This paper presents a large language model (LLM)-based framework that adapts and fine-tunes compact LLMs for detecting cyberattacks on transformer current differential relays (TCDRs), which can otherwise cause false tripping of critical power transformers. The core idea is to textualize multivariate time-series current measurements...
Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thinking approaches often lead to overthinking, where models produce excessively verbose responses even for simple queries, resulting in test-time inefficiency...
Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form coherent combinations. Existing approaches either simplify policy learning by assuming independence across sub-actions, which often yields incoherent or invalid...
To predict what someone will say is to model how they think. We study this through next-turn dialogue prediction: given a conversation, predict the next utterance produced by a person. We compare learning approaches along two dimensions: (1) whether the model is allowed to think before responding, and (2) how learning is rewarded...
Large language models (LLMs) frequently fail to challenge users' harmful beliefs in domains ranging from medical advice to social reasoning. We argue that these failures can be understood and addressed pragmatically as consequences of LLMs defaulting to accommodating users' assumptions and exhibiting insufficient epistemic vigilance....
The integration of multicarrier modulation and multiple-input-multiple-output (MIMO) is critical for reliable transmission of wireless signals in complex environments, which significantly improve spectrum efficiency. Existing studies have shown that popular orthogonal time frequency space (OTFS) and affine frequency division...
Many operational systems collect high-dimensional timeseries data about users/systems on key performance metrics. For instance, ISPs, content distribution networks, and video delivery services collect quality of experience metrics for user sessions associated with metadata (e.g., location, device, ISP). Over such historical data,...
In recent years, deep learning has attracted increasing attention in the field of Cardiac MRI (CMR) reconstruction due to its superior performance over traditional methods, particularly in handling higher acceleration factors, highlighting its potential for real-world clinical applications. However, current deep learning methods...
Modern LLM agents increasingly rely on dynamic structured generation, such as tool calling and response protocols. Unlike traditional structured generation with static structures, these workloads vary both across requests and within a request, posing new challenges to existing engines. We present XGrammar-2, a structured generation...
Large language models (LLMs) now support contexts of up to 1M tokens, but their strengths and weaknesses on complex long-context tasks remain unclear. To study this, we focus on multi-document legal case summarization, where a single case often spans many documents exceeding 100K tokens. We systematically evaluate 12 frontier LLMs...