PreprintNot peer reviewedArtificial IntelligenceA preprint maps shared safety pathways that link LLM refusal across languagesOriginal title: Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety PathwaysResearchers report locating cross-layer safety pathways shared between high- and low-resource languages, then tuning just these to cut unsafe outputs.Shuyi Miao et al. · Added 26 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint outlines quantum algorithm for thermal states of Bose-Hubbard modelsOriginal title: Simulating Thermal Properties of Bose-Hubbard Models on a Quantum ComputerA preprint reports a mathematically grounded method to prepare thermal states for bosonic many-body systems using quantum hardware.Simon Becker et al. · Added 26 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports a single tunable SWAP gate can run universal quantum computationOriginal title: The Power of Power-of-SWAP: Postselected Quantum Computation with the Exchange InteractionResearchers propose a restricted circuit model using only the exchange interaction and show the square-root-SWAP gate alone is universal.Jędrzej Burkat et al. · Added 26 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report LLMs become easier to jailbreak when induced to use ‘drunk’ languageOriginal title: In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language InducementA preprint finds that making LLMs mimic drunken text raises jailbreak and privacy-leak rates across five models.Anudeex Shetty et al. · Added 26 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports SLM ensembles beating a flagship LLM on instruction-followingOriginal title: Beyond Leaderboards: Tokenomics of Agentic Small Language Model EnsemblesA preprint finds small-model ensembles with a judge-feedback loop outperform a flagship LLM on instruction tests, at lower cost.Alexei N. Skurikhin et al. · Added 26 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report taxonomy-guided prompting beats fine-tuning for OSS threat detectionOriginal title: Autonomous OSS Threat Detection via Taxonomy-Aligned LLMsA preprint reports that structured prompting with GPT-4 outperforms fine-tuned models in classifying open source supply chain threats.Md. Robiul Islam Niloy · Added 26 Oct 2026
Journal articleReview status unknownQuantum ComputingResearchers test quantum-computer simulation of a simple correlated-electron modelOriginal title: Variational quantum-algorithm based self-consistent calculations for the two-site DMFT model on noisy quantum computing hardwareA study examines using a variational quantum algorithm on real quantum hardware to solve a minimal DMFT model, finding noise still limits accuracy.Jannis Ehrlich et al. · Added 26 Oct 2026 · Released May 2025
PreprintNot peer reviewedArtificial IntelligenceA preprint maps RAG research into four axes: efficiency, defence, interaction, reasoningOriginal title: Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and ReasoningA survey organises retrieval-augmented generation research into efficiency, security, interactivity and reasoning, highlighting gaps for future work.Meghana Sunil et al. · Added 26 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report noise-injection trick to run oversized quantum Born machines on smaller chipsOriginal title: Deployment of Large IQP Circuit Born Machines on Qubit-Limited Hardware Using Noise InjectionA preprint describes injecting noise into large IQP quantum circuits so they can be sampled on smaller quantum processors, with mitigation restoring accuracy.Ju-Young Ryu et al. · Added 26 Oct 2026
PreprintNot peer reviewedFrom HuaweiArtificial IntelligenceA preprint reports worst-case constraints fix reward hacking in LLM reasoning distillationOriginal title: The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement LearningResearchers propose a constrained RL method that blocks students from masking a single bad reasoning step with good ones elsewhere.Added 26 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint explores small quantum heads for cybersecurity threat detectionOriginal title: Quantum Machine Learning for Cybersecurity Applications: Simulation and Hardware ValidationA preprint reports that compact quantum models matched or slightly beat classical ones on two cybersecurity tasks, with hardware tests tracking simulations closely.Zirui Zhu et al. · Added 26 Oct 2026
Journal articleReview status unknownQuantum ComputingResearchers propose hybrid VQE-CVQE quantum algorithm using diabatic state preparationOriginal title: Hybrid VQE-CVQE algorithm using diabatic state preparationA study proposes a hybrid VQE-CVQE quantum algorithm and reports accurate simulated energies on an IBM quantum processor.John P. T. Stenger et al. · Added 26 Oct 2026 · Released Jun 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report fine-tuned small models can support ED triage decisionsOriginal title: Domain-Adapted Small Language Models for Reliable Clinical TriageA preprint reports a fine-tuned 7B open-source model outperformed larger proprietary LLMs at predicting emergency triage levels.Manar Aljohani et al. · Added 26 Oct 2026
Conference paperReview status unknownQuantum ComputingResearchers report adaptive post-quantum crypto scheme for 6G vehicle networksOriginal title: Adaptive Quantum-Safe Cryptography for 6G Vehicular Networks via Context-Aware OptimizationA preprint proposes a context-aware system that switches post-quantum cryptography schemes in vehicle networks to balance speed and security.Poushali Sengupta et al. · Added 26 Oct 2026 · Released Jan 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose a Bayesian method for scoring trust in multi-LLM debate councilsOriginal title: Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent AdversariesA preprint reports a new way to weigh AI model opinions by reliability, improving calibration and resistance to persistent bad actors.Ionel Eduard Stan et al. · Added 26 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint finds multi-agent LLM coding tools cost far more energy for little accuracy gainOriginal title: Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer WorkflowsA preprint reports that multi-agent LLM setups for coding tasks use much more energy and time than simple single queries, with limited accuracy benefit.Merve Astekin et al. · Added 26 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint proposes a formula predicting when combining LLMs helps or hurtsOriginal title: Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble LiftA preprint presents a tested formula for predicting when pooling LLM votes improves or worsens accuracy.Junade Ali · Added 26 Oct 2026
Conference paperReview status unknownQuantum ComputingResearchers propose satellite-assisted entanglement pre-distribution for quantum networksOriginal title: Satellite-Aided Entanglement Distribution for Optimized Quantum NetworksA conference paper reports that adding satellite links to pre-distributed quantum entanglement can cut resource use in small networks.Jakob Kaltoft Søndergaard et al. · Added 26 Oct 2026 · Released Feb 2025
PreprintNot peer reviewedArtificial IntelligenceResearchers report no single AI architecture wins at every scale of red-team simulationOriginal title: No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team AgentsA preprint finds reinforcement-learning and language-model red-team agents each dominate in different cyberattack-simulation environments, not universally.Ayan Javeed Shaikh et al. · Added 26 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA participatory framework links AI lifecycle biases to specific anticipated harmsOriginal title: ECHO: A Participatory Framework for Bias-Anchored AI Harm AnticipationA preprint proposes ECHO, a framework that elicits how stakeholders link AI biases to potential harms in diagnosis and hiring.Nicoleta Tantalaki et al. · Added 26 Oct 2026
