Stay updated with the latest research and technology news
arXiv:2601.20125v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility...
arXiv:2601.20126v1 Announce Type: new Abstract: Large Language Models (LLMs) often produce hallucinated or unverifiable content, undermining their reliability in factual domains. This work investigates Reinforcement...
arXiv:2601.20129v1 Announce Type: new Abstract: Sentiment analysis for the Bengali language has attracted increasing research interest in recent years. However, progress remains constrained by the...
arXiv:2601.20130v1 Announce Type: new Abstract: Real-time execution is essential for cyber-physical systems such as robots. These systems operate in dynamic real-world environments where even small...
arXiv:2601.20131v1 Announce Type: new Abstract: Designing an embedding retrieval system requires navigating a complex design space of conflicting trade-offs between efficiency and effectiveness. This work...
arXiv:2601.20135v1 Announce Type: new Abstract: This paper gives an overview of the use of control systems engineering in synthetic biology, motivated by applications such as...
arXiv:2601.20137v1 Announce Type: new Abstract: We present a dynamic framework for maintaining $k$-edge-connectivity of undirected, simple graphs subject to structural updates, specifically single edge additions...
arXiv:2601.20138v1 Announce Type: new Abstract: We present a large autoregressive model for source-space MEG that scales next-token prediction to long context across datasets and scanners:...
arXiv:2601.20141v1 Announce Type: new Abstract: Although most people support climate action, widespread underestimation of others' support stalls individual and systemic changes. In this preregistered experiment,...
arXiv:2601.20142v1 Announce Type: new Abstract: Self-supervised learning (SSL) models have achieved impressive results across many speech tasks, yet child automatic speech recognition (ASR) remains challenging...
arXiv:2601.20144v1 Announce Type: new Abstract: Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with...
arXiv:2601.20145v1 Announce Type: new Abstract: A priori and a posteriori error analysis of $hp$ finite element method for elliptic control problem with Robin boundary condition...
arXiv:2601.20147v1 Announce Type: new Abstract: Instruction-tuned Language Models ILMs have become essential components of modern AI systems, demonstrating exceptional versatility across a wide range of...
arXiv:2601.20148v1 Announce Type: new Abstract: Logs are essential for understanding Continuous Integration (CI) behavior, particularly for diagnosing build failures and performance regressions. Yet their growing...
arXiv:2601.20149v1 Announce Type: new Abstract: Gaussian Processes (GPs) are powerful non-parametric Bayesian models for regression of scalar fields, formulated under the assumption that measurement locations...
arXiv:2601.20154v1 Announce Type: new Abstract: Self-supervised learning (SSL) have improved empirical performance by unleashing the power of unlabeled data for practical applications. Specifically, SSL extracts...
arXiv:2601.20157v1 Announce Type: new Abstract: Pairwise-constrained clustering augments unsupervised partitioning with side information by enforcing must-link (ML) and cannot-link (CL) constraints between specific samples, yielding...
arXiv:2601.20158v1 Announce Type: new Abstract: Most of the current software security analysis tools assess vulnerabilities in isolation. However, sophisticated software supply chain security threats often...
arXiv:2601.20160v1 Announce Type: new Abstract: Software development agents such as Claude Code, GitHub Copilot, Cursor Agent, Devin, and OpenAI Codex are being increasingly integrated into...
arXiv:2601.20161v1 Announce Type: new Abstract: People candidly discuss sensitive topics online under the perceived safety of anonymity; yet, for many, this perceived safety is tenuous,...
arXiv:2601.20162v1 Announce Type: new Abstract: Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while...
arXiv:2601.20163v1 Announce Type: new Abstract: Always-on hardware Trojans (HTs) pose a critical risk to trusted microelectronics, yet most side-channel detection methods rely on unavailable golden...
arXiv:2601.20164v1 Announce Type: new Abstract: Prior work suggests that language models, while trained on next token prediction, show implicit planning behavior: they may select the...
arXiv:2601.20168v1 Announce Type: new Abstract: Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention...