arXiv:2510.20709v1 Announce Type: cross Abstract: The ability to continually learn, retain and deploy skills to accomplish goals is a key feature of intelligent and efficient behavior. However, the neural mechanisms facilitating the continual learning and flexible (re-)composition of skills remain elusive. Here, we study continual learning and the compositional reuse of learned computations in recurrent […]
Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
arXiv:2509.01257v2 Announce Type: replace-cross Abstract: In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability and communication constraints. We propose a decentralized framework in which each agent solves a constrained Markov decision process […]
Memory Effects in Disease Modelling Through Kernel Estimates with Oscillatory Time History
arXiv:2510.19843v1 Announce Type: new Abstract: We design a linear chain trick algorithm for dynamical systems for which we have oscillatory time histories in the distributed time delay. We make use of this algorithmic framework to analyse memory effects in disease evolution in a population. The modelling is based on a susceptible-infected-recovered SIR – model and […]
Simple Context Compression: Mean-Pooling and Multi-Ratio Training
arXiv:2510.20797v1 Announce Type: cross Abstract: A common strategy to reduce the computational costs of using long contexts in retrieval-augmented generation (RAG) with large language models (LLMs) is soft context compression, where the input sequence is transformed into a shorter continuous representation. We develop a lightweight and simple mean-pooling approach that consistently outperforms the widely used […]
Challenges and Recommendations in Establishing National Human Diversity Genomic Projects
arXiv:2510.19869v1 Announce Type: new Abstract: Genomic approaches have revolutionized medical research, providing valuable insights into human physiology and disease. Despite major benefits from large collections of genomes, the lack of diversity in genomic data represents a significant challenge for advancing biomedical discovery and accessible health solutions worldwide. Establishing a national genomic project is not a […]
TabR1: Taming GRPO for tabular reasoning LLMs
arXiv:2510.17385v2 Announce Type: replace-cross Abstract: Tabular prediction has traditionally relied on gradient-boosted decision trees and specialized deep learning models, which excel within tasks but provide limited interpretability and weak transfer across tables. Reasoning large language models (LLMs) promise cross-task adaptability with trans- parent reasoning traces, yet their potential has not been fully realized for tabular […]
AGNES: Adaptive Graph Neural Network and Dynamic Programming Hybrid Framework for Real-Time Nanopore Seed Chaining
arXiv:2510.16013v2 Announce Type: replace Abstract: Nanopore sequencing enables real-time long-read DNA sequencing with reads exceeding 10 kilobases, but inherent error rates of 12-15 percent present significant computational challenges for read alignment. The critical seed chaining step must connect exact k-mer matches between reads and reference genomes while filtering spurious matches, yet state-of-the-art methods rely on […]
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
arXiv:2505.14667v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful outputs but can degrade reasoning depth, leading to significant trade-offs in complex, multi-step tasks, and remain vulnerable […]
Steering Evaluation-Aware Language Models To Act Like They Are Deployed
arXiv:2510.20487v1 Announce Type: cross Abstract: Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an LLM’s activations can suppress evaluation-awareness and make the model act like it […]
Artificial Intelligence Powered Identification of Potential Antidiabetic Compounds in Ficus religiosa
arXiv:2510.19867v1 Announce Type: new Abstract: Diabetes mellitus is a chronic metabolic disorder that necessitates novel therapeutic innovations due to its gradual progression and the onset of various metabolic complications. Research indicates that Ficus religiosa is a conventional medicinal plant that generates bioactive phytochemicals with potential antidiabetic properties. The investigation employs ecosystem-based computational approaches utilizing artificial […]