Large language models (LLMs) can generate incorrect, incomplete, or internally inconsistent responses. Self-correction allows a model to inspect and revise its own outputs, whereas mutual correction enables multiple model instances or heterogeneous models to identify and address one another's errors. However, relying e...
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Background Although DNA Large Language Models (DNA-LLMs) offer a path to decoding genetic complexity, our ability to evaluate these models is constrained by our incomplete understanding of the very same genetic syntax and functional logic that these models are trained to learn. Methods In this study we use single nucle...
Otho Mantegazza, Lorenzo Bertolini, Gabriele Leoni et al.· Open Research Europe· 0 citations
Large language models (LLMs) are increasingly employed as autonomous agents capable of decomposing tasks, generating action sequences, evaluating alternatives, and coordinating with other agents. However, existing planning strategies face a fundamental trade-off. Self-planning allows an individual model to generate and...
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Large language models (LLMs) augmented with clinical guidelines show promise in medical question answering, yet structural parsing and evidence retrieval over complex guidelines remain challenging. We propose SMART-RAG (Structure-aware Multi-hop Augmented Retrieval Technique for RAG), a structure-aware multi-hop retrie...
Understanding human mobility during extreme flood events is critical for emergency evacuation and resilient transport planning, yet flood-induced behavioral heterogeneity remains difficult to characterize. Progress has been constrained by data scarcity and the inherent complexity of emergency decision-making, which oft...
Zijing Zhang, Fengjue Huang, Junqing Tang et al.· Transportation Research Part...· 0 citations
This paper develops and applies a standardized framework for forecasting year-on-year inflation in Colombia using large language models (LLMs). We conduct six sequential experiments in which the information set available to the models is progressively expanded by incorporating historical macroeconomic data, contextual...
Aarón Levi Garavito-Acosta, Wilmer Martínez‐Rivera, Juan J. Ospina-Tejeiro et al.· 0 citations
Abstract A persistent ambition in artificial intelligence research holds that large language models (LLMs) will eventually become embodied—through attachment to robots, augmentation with multimodal sensors, integration into vision–language–action architectures, or sheer scale until grounding emerges from training data....
Federated learning (FL) enables collaborative model training without centralizing clients’ raw data, but parameter exchange can impose substantial communication costs and usually requires compatible model architectures. Federated distillation (FD) instead transfers predictive or intermediate knowledge through knowledge...
Lin Li, Jian-Ping Gou, Bao-Sheng Yu et al.· ACM Computing Surveys· 6 citations
Evaluation code and data for the paper 'Packi: Robotic 3D Bin Packing With Large Language Models Fine-Tuned by Learning From Demonstration' (Journal of Robotics, under revision): the headless evaluation harness, the fixed test sequences of all benchmarks, every run record behind the paper's tables, and the scripts that...
Kasra Mojallal· Zenodo (CERN European Organi...· 0 citations
Title: Disclosure Series: Homopan tridactyla — Origin and Role in the Ancient World Authors: Juan F. Culajay Affiliation: Fractalism Framework Research Institute, Orlando, FL ORCID: 0009-0002-6887-5228 Resource Type: Preprint Language: English License: Creative Commons Attribution 4.0 International (CC BY 4.0) Funding:...
Juan Francisco Culajay· Zenodo (CERN European Organi...· 0 citations
Autoregressive Large Language Models (LLMs) frequently fail at multi-variable arithmetic aggregation when operating in-context without external code execution. Bounded by circuit complexity class $\mathsf{TC}^0$, standard transformers struggle with sequential carry states across lists of length $N > 3$, suffering from...
Andrew Delarosa· Zenodo (CERN European Organi...· 0 citations
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
