PreprintNot peer reviewedArtificial IntelligencePreprint reports small language models boosting intrusion detection via structured rulesOriginal title: SERA-IDS: Structured Experience Retrieval-Augmented Intrusion Detection with Small Language ModelsResearchers report that adding structured, error-derived rules sharply raises Macro-F1 for small language models detecting network intrusions.Md Shamimul Islam et al. · Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report symmetry-based method for building optimal quantum transducersOriginal title: Optimal transducers using symmetriesA preprint shows how exploiting problem symmetries simplifies designing optimal transducers for quantum query algorithms.Benoît Dubus et al. · Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report parallel bit-flipping boost for quantum LDPC belief propagation decodingOriginal title: Learned Parallel Bit-Flipping Sequential Belief Propagation Decoding of Quantum LDPC CodesA preprint describes a decoder that branches learned sequential belief propagation in parallel to improve quantum LDPC code reliability without added latency.Mohsen Moradi et al. · Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports optimal two-mode bosonic codes built from finite-group symmetryOriginal title: Optimal two-mode bosonic loss codes from finite group symmetryA preprint finds that optimal numerically discovered photon-loss codes share finite-group structure, which the authors turn into exact constructions.Argyris Giannisis Manes et al. · Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint describes CacheTune, a system for reusing non-prefix KV caches in long-context LLM servingOriginal title: Adaptive KV Cache Reuse for Fast Long-Context LLM ServingA preprint reports a frequency-guided KV cache reuse system that speeds up long-context LLM serving while preserving output quality.Fei li et al. · Added 25 Oct 2026
PreprintNot peer reviewedFrom Crusoe AIArtificial IntelligenceResearchers report faster LLM decoding via asymmetric key-value attention designOriginal title: More Value per Key: Asymmetric Sparse Attention for Faster LLM DecodingA preprint describes an attention method that cuts decoding costs by using fewer key heads than value heads under sparsity.Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint proposes multi-spin molecules to correct both dephasing and relaxation errorsOriginal title: Beyond Pure Dephasing: Quantum Error Correction in Single Molecules Requires Multiple SpinsResearchers outline a two-level molecular spin scheme that corrects both dephasing and relaxation noise for fault-tolerant qubits.Matteo Mezzadri et al. · Added 25 Oct 2026
PreprintNot peer reviewedFrom Google Quantum AIQuantum ComputingPreprint proposes multivariate quantum signal processing for several matrices at onceOriginal title: Multivariate Quantum Signal ProcessingA preprint reports a framework for designing quantum circuits that jointly transform several noncommuting block-encoded matrices.Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report internal signals can detect and curb unsafe CLI agent actionsOriginal title: Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI AgentsA preprint proposes reading an LLM agent's hidden states step-by-step to catch and steer away from harmful command-line actions.Weidi Luo et al. · Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports faster, leaner circuit design for quantum error-correction codesOriginal title: SpiderCSS: Scalable Fault-Tolerant CSS State PreparationA preprint describes SpiderCSS, a scalable method for building fault-tolerant state-preparation circuits for CSS quantum codes.Boldizsár Poór et al. · Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report rhetorical tricks can sway human judges in AI safety debatesOriginal title: AI Safety via Debate is Compromised by Cognitive BiasesA preprint reports that cognitive-bias tactics like jargon and verbosity shifted human judgments in AI debate experiments, even when the manipulated side was wrong.Gefei Liu et al. · Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report a black-box attack method for testing LLM jailbreak defencesOriginal title: All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable … AttacksA preprint presents a diffusion-model-based attacker the authors say works across undefended, defended and API-hosted LLMs without model access.Vincent Limbach et al. · Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report a universal scheme for converting unknown qubit states into magic statesOriginal title: Universal magic state concentrationA preprint describes a fixed stabilizer protocol that turns a few copies of an unknown pure qubit state into an exact CCZ magic state.Jacopo Rizzo et al. · Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report LLMs often get vulnerability verdicts right for flawed reasonsOriginal title: Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability ReasoningA preprint finds correct vulnerability verdicts from LLMs often hide fabricated reasoning that free-form judges miss.Boyue Caroline Hu et al. · Added 25 Oct 2026
PreprintNot peer reviewedFrom Citigroup, Ernst & Young, NVIDIAArtificial IntelligenceA preprint proposes a framework to test enterprise AI workflows before scaling themOriginal title: EnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the EnterpriseA preprint presents EnterpriseVal, a system for assessing whether generative AI workflows are fit, reliable and worth scaling inside a firm.Added 25 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report a low-overhead way to encrypt federated training of quantum neural networksOriginal title: Encryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural NetworksA preprint reports that switching to quaternion coordinates lets encrypted quantum neural network training avoid costly bootstrapping with no measurable accuracy loss.Marcel Mordarski et al. · Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint finds small LLMs cave fast to persuasion, confidence prompts backfireOriginal title: Vulnerability of LLMs' Stated Beliefs? LLMs Belief Resistance Check Through Strategic Persuasive Conversation InterventionsA preprint reports that LLM belief stability under persuasion varies widely by model, and that asking for confidence scores makes some models more, not less, vulnerable.Fan Huang et al. · Added 25 Oct 2026
PreprintNot peer reviewedFrom QuEra ComputingQuantum ComputingResearchers report symmetry-preserving method for compiling quantum simulationsOriginal title: Symmetry-preserving quantum compilationA preprint describes a compilation scheme that keeps SU(2) symmetry exact while cutting gate costs for simulating quantum magnetism.Added 25 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint predicts LLM code maintainability before generationOriginal title: PreMaQ: Predicting Maintainability-Related Quality of LLM-Generated Code Before GenerationA preprint reports a method that predicts code smell and maintainability scores from an LLM's internal state before code is generated.Taiki Wakamatsu et al. · Added 25 Oct 2026
PreprintNot peer reviewedFrom BaiduArtificial IntelligenceResearchers propose entropy-based filtering to stabilise asynchronous LLM reinforcement learningOriginal title: Deconstructing Off-Policy Ratios: Entropy-Normalized Trust Regions for Asynchronous Reinforcement LearningA preprint proposes scaling the trust region for off-policy updates by token entropy to stabilise asynchronous RL training.Added 25 Oct 2026
