arXiv:2510.20566v1 Announce Type: cross Abstract: Existing defence mechanisms have demonstrated significant effectiveness in mitigating rule-based Denial-of-Service (DoS) attacks, leveraging predefined signatures and static heuristics to identify and block malicious traffic. However, the emergence of AI-driven techniques presents new challenges to SDN security, potentially compromising the efficacy of existing defence mechanisms. In this paper, we introduce~AdaDoS, […]
DAG-Math: Graph-Guided Mathematical Reasoning in LLMs
arXiv:2510.19842v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate strong performance on mathematical problems when prompted with Chain-of-Thought (CoT), yet it remains unclear whether this success stems from search, rote procedures, or rule-consistent reasoning. To address this, we propose modeling CoT as a certain rule-based stochastic process over directed acyclic graphs (DAGs), where nodes […]
Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection
arXiv:2510.20653v1 Announce Type: cross Abstract: As Large Language Models (LLMs) continue to evolve, practitioners face increasing options for enhancing inference-time performance without model retraining, including budget tuning and multi-step techniques like self-reflection. While these methods improve output quality, they create complex trade-offs among accuracy, cost, and latency that remain poorly understood across different domains. This […]
Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
arXiv:2510.19838v1 Announce Type: new Abstract: Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical embodied reasoning in open web environments. However, existing approaches remain limited in reasoning depth and efficiency: vanilla […]
Collective Communication for 100k+ GPUs
arXiv:2510.20171v1 Announce Type: cross Abstract: The increasing scale of large language models (LLMs) necessitates highly efficient collective communication frameworks, particularly as training workloads extend to hundreds of thousands of GPUs. Traditional communication methods face significant throughput and latency limitations at this scale, hindering both the development and deployment of state-of-the-art models. This paper presents the […]
Benchmarking Reasoning Reliability in Artificial Intelligence Models for Energy-System Analysis
arXiv:2510.19836v1 Announce Type: new Abstract: Artificial intelligence and machine learning are increasingly used for forecasting, optimization, and policy design in the energy sector, yet no standardized framework exists to evaluate whether these systems reason correctly. Current validation practices focus on predictive accuracy or computational efficiency, leaving the logical integrity of analytical conclusions untested. This study […]
QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models
arXiv:2510.20222v1 Announce Type: cross Abstract: In real-world time series forecasting tasks, category information plays a pivotal role in capturing inherent data patterns. This paper introduces QKCV (Query-Key-Category-Value) attention, an extension of the traditional QKV framework that incorporates a static categorical embedding C to emphasize category-specific information. As a versatile plug-in module, QKCV enhances the forecasting […]
Autoencoding Random Forests
arXiv:2505.21441v2 Announce Type: replace-cross Abstract: We propose a principled method for autoencoding with random forests. Our strategy builds on foundational results from nonparametric statistics and spectral graph theory to learn a low-dimensional embedding of the model that optimally represents relationships in the data. We provide exact and approximate solutions to the decoding problem via constrained […]
Context-level Language Modeling by Learning Predictive Context Embeddings
arXiv:2510.20280v1 Announce Type: cross Abstract: Next-token prediction (NTP) is the cornerstone of modern large language models (LLMs) pretraining, driving their unprecedented capabilities in text generation, reasoning, and instruction following. However, the token-level prediction limits the model’s capacity to capture higher-level semantic structures and long-range contextual relationships. To overcome this limitation, we introduce textbfContextLM, a framework […]
Transforming Multi-Omics Integration with GANs: Applications in Alzheimer’s and Cancer
arXiv:2510.19870v1 Announce Type: new Abstract: Multi-omics data integration is crucial for understanding complex diseases, yet limited sample sizes, noise, and heterogeneity often reduce predictive power. To address these challenges, we introduce Omics-GAN, a Generative Adversarial Network (GAN)-based framework designed to generate high-quality synthetic multi-omics profiles while preserving biological relationships. We evaluated Omics-GAN on three omics […]