arXiv preprints from January 1, 2026 through September 27, 2026 — 00:32:40 EST
The rigorous security model of Bitcoin's UTXO architecture often comes at the cost of developer usability, forcing a reliance on manual stack manipulation that leads to critical financial vulnerabilities like signature malleability, unspendable states and unconstrained execution paths. Industry standards such as Miniscript provide...
Neural Radiance Fields (NeRF) achieve remarkable performance in dense multi-view scenarios, but their reconstruction quality degrades significantly under sparse inputs due to geometric artifacts. Existing methods utilize global depth regularization to mitigate artifacts, leading to the loss of geometric boundary details. To address...
We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g., mid-training, SFT, reinforcement learning, and their combinations), we explore how to push the limits...
Video Face Swapping (VFS) requires seamlessly injecting a source identity into a target video while meticulously preserving the original pose, expression, lighting, background, and dynamic information. Existing methods struggle to maintain identity similarity and attribute preservation while preserving temporal consistency. To address...
Understanding the interaction of neural and cardiac systems during cognitive activity is critical to advancing physiological computing. Although EEG has been the gold standard for assessing mental workload, its limited portability restricts its real-world use. Widely available ECG through wearable devices proposes a pragmatic...
Artificial General Intelligence (AGI) may face a confrontation question: under what conditions would a rationally self-interested AGI choose to seize power or eliminate human control (a confrontation) rather than remain cooperative? We formalize this in a Markov decision process with a stochastic human-initiated shutdown event....
Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications that focus mainly on harmfulness, leading to substantial overestimation of attack success. To address this problem, we propose FJAR, a fine-grained jailbreak...
System-level telemetry is fundamental to modern remote monitoring, predictive maintenance, and AI-driven infrastructure optimisation. Existing telemetry encodings such as JSON, JSON Lines, CBOR, and Protocol Buffers were designed for high-bandwidth, always-online environments. They impose significant overhead when deployed in...
This paper introduces a novel technique to preserve spectral features in lossy compression based on a novel fast Fourier correction algorithm\added{ for regular-grid data}. Preserving both spatial and frequency representations of data is crucial for applications such as cosmology, turbulent combustion, and X-ray diffraction, where...
Manual font design is an intricate process that transforms a stylistic visual concept into a coherent glyph set. This challenge persists in automated Few-shot Font Generation (FFG), where models often struggle to preserve both the structural integrity and stylistic fidelity from limited references. While autoregressive (AR) models...
We demonstrate SAGE-32B, a 32 billion parameter language model that focuses on agentic reasoning and long range planning tasks. Unlike chat models that aim for general conversation fluency, SAGE-32B is designed to operate in an agentic loop, emphasizing task decomposition, tool usage, and error recovery. The model is initialized from...
The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for systematic evaluation. To address...
In recent years, cyberattacks - along with physical faults - have become an increasing factor causing system failures, especially in DER (Distributed Energy Resources) systems. In addition, according to the literature, a number of faults have been reported to remain undetected. Consequently, unlike anomaly detection works that only...
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...
We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks control collapse. We also distinguish between authorized steerability (builders reliably reaching...
The growth of Electric Vehicles (EVs) creates a conflict in vehicle-to-building (V2B) settings between building operators, who face high energy costs from uncoordinated charging, and drivers, who prioritize convenience and a full charge. To resolve this, we propose a negotiation-based framework that, by design, guarantees voluntary...
Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how a unified optimization objective gives rise to functionally distinct capabilities of generating solutions and evaluating when to revise them remains opaque....
Accurate vehicle positioning requires effective IMU-GPS fusion, yet prior methods-EKF, UKF, ML, GA, and DE-suffer from nonlinearity, instability, or high computational cost. This study introduces a PSO-based adaptive tuning framework for optimizing UKF parameters (α, \b{eta}, \k{appa}, Q, R), evaluated in CARLA 0.9.14 using a Tesla...
Current attempts of Reinforcement Learning for Autonomous Controller are data-demanding while the results are under-performed, unstable, and unable to grasp and anchor on the concept of safety, and over-concentrating on noise features due to the nature of pixel reconstruction. While current Self-Supervised Learningapproachs that...
Evaluating novelty is critical yet challenging in peer review, as reviewers must assess submissions against a vast, rapidly evolving literature. This report presents OpenNovelty, an LLM-powered agentic system for transparent, evidence-based novelty analysis. The system operates through four phases: (1) extracting the core task and...
LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift. We present CaveAgent, a framework that shifts tool use from ``LLM-as-Text-Generator'' to...
Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity-preserving speech. Existing approaches either suffer from temporal misalignment due to cascaded generation or lack the capability to perform zero-shot...
We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora. Logics-STEM targets reasoning tasks in the domains of Science, Technology, Engineering, and Mathematics...
This paper addresses the problem of accurate localization for quadrupedal robots operating in narrow tunnel-like environments. Due to the long and homogeneous characteristics of such scenarios, LiDAR measurements often provide weak geometric constraints, making traditional sensor fusion methods susceptible to accumulated motion...
Predicting river flow in places without streamflow records is challenging because basins respond differently to climate, terrain, vegetation, and soils. Traditional basin attributes describe some of these differences, but they cannot fully represent the complexity of natural environments. This study examines whether AlphaEarth...