PreprintNot peer reviewedArtificial IntelligenceA preprint proposes selective layer recovery to defend LLMs against malicious fine-tuningOriginal title: SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic RoutingResearchers report a defense that routes a small safety adapter to malicious queries, cutting harmful outputs while keeping task accuracy.Hui Zhang et al. · Added 10 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint describes hardware-aware quantum circuit-cutting method for data encodingOriginal title: Quantum Data Representation via Circuit Partitioning and ReintegrationA preprint presents shardQ, a method that cuts and reconstructs quantum circuits to reduce errors from poor qubit connectivity.Ziqing Guo et al. · Added 10 Nov 2026
PreprintNot peer reviewedFrom MicrosoftArtificial IntelligenceA preprint reports self-play method lets small models match larger ones at spotting hallucinationsOriginal title: Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved GeneratorResearchers describe a self-play framework where a generator and detector co-evolve to improve hallucination detection without extra human labels.Added 10 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers report compact on-chip dissipator for fast superconducting qubit resetOriginal title: Resetting a Superconducting Qubit with a Compact Colder Resistive Dissipator below the Qubit FrequencyA preprint describes a compact resistor-based dissipator that resets a superconducting qubit without extra control lines.Jiajia Tian et al. · Added 10 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports smarter rollout budgeting improves search-agent training accuracyOriginal title: Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn Search AgentsResearchers propose allocating RL rollout computation by intermediate-state informativeness, reporting accuracy gains on search QA benchmarks.Yijun Zhang et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint describes a defence against malware hidden inside shared neural network weightsOriginal title: NeuPerm: Disrupting Malware Hidden in Neural Network Parameters by Leveraging Permutation SymmetryResearchers report a method called NeuPerm that permutes neural network parameters to disrupt hidden malware without hurting model accuracy.Daniel Gilkarov et al. · Added 9 Nov 2026
Journal articleReview status unknownQuantum ComputingReview maps cryoelectronics options for scaling superconducting fault-tolerant quantum computersOriginal title: Integration and Resource Estimation of Cryoelectronics for Superconducting Fault-Tolerant Quantum ComputersA review surveys cryogenic control electronics and offers first-order estimates for scaling superconducting fault-tolerant quantum computers.Shiro Kawabata · Added 9 Nov 2026 · Released May 2026
PreprintNot peer reviewedFrom Alibaba GroupArtificial IntelligenceResearchers propose a graph-based method to trace failures in LLM memory systemsOriginal title: MemTrace: Tracing and Attributing Errors in Large Language Model Memory SystemsA preprint introduces MemTrace, a framework and benchmark for pinpointing which operation caused an LLM memory system to fail.Added 9 Nov 2026
PreprintNot peer reviewedFrom NEC Laboratories AmericaArtificial IntelligenceResearchers report skill-distilling reinforcement learning boosts LLM agent performanceOriginal title: SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement LearningA preprint describes SkillRL, which turns agent trajectories into reusable skills during reinforcement learning, reportedly beating memory-based baselines.Added 9 Nov 2026
PreprintNot peer reviewedFrom FreeYa Mind CampusQuantum ComputingA preprint benchmarks how quantum circuit optimizers split search direction from update rulesOriginal title: Benchmarking Modular Optimization Strategies for Parameterized Quantum CircuitsResearchers report that no single optimizer or update rule dominates across quantum workloads when evaluation cost and seed variability are considered.Added 9 Nov 2026
PreprintNot peer reviewedFrom Lexsi LabsArtificial IntelligencePreprint presents AuditKIT, a unified toolkit for evaluating language models and agentsOriginal title: AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic SystemsA preprint describes AuditKIT, a source-available library that unifies benchmarking, judging, and agent evaluation into one measurement framework.Added 9 Nov 2026
PreprintNot peer reviewedFrom Autolab AIArtificial IntelligenceResearchers report LLMs can partly predict which ML ideas will actually workOriginal title: Can LLMs predict the outcomes of machine learning experiments?A preprint finds frontier LLMs forecast ML experiment outcomes better than chance but still miss much of the variation.Added 9 Nov 2026
PreprintNot peer reviewedQuantum ComputingReview argues AI helps quantum optimisation more than quantum helps AIOriginal title: Beyond QAOA: A Review of AI and Quantum Computing for Adaptive Combinatorial OptimizationA preprint review of 119 papers finds AI consistently improves quantum optimisation pipelines, while the reverse direction stays mostly simulated.Hoong Chuin LAU · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report multi-agent system with dual memory speeds up GPU kernel optimisationOriginal title: KernelClaw: A Multi-Agent Framework for GPU Kernel Optimization with Dual-Memory MechanismsA preprint describes KernelClaw, a multi-agent framework using expert knowledge and trajectory memory to optimise GPU kernels faster than prior methods.Qitong Sun et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers find Bangla safety filters fail more when prompts are romanised or code-mixedOriginal title: BanglaShield: A Script-Robust Safety Classifier and Benchmark for Bangla Native, Romanized, and Code-Mixed PromptsA preprint reports LLM safety classifiers miss many unsafe Bangla prompts, especially when romanised, and introduces a compact classifier that performs more consistently.Mohsinul Kabir et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report a quality-diversity approach boosts research idea generation with LLM agentsOriginal title: IDEAgent: Agentic Quality-Diversity Search for Research Idea GenerationA preprint presents IDEAgent, a multi-agent system that the authors say generates more diverse, high-quality research ideas than prior methods.Varun Gumma et al. · Added 9 Nov 2026
PreprintNot peer reviewedFrom RopediaArtificial IntelligenceResearchers report a cross-embodiment world model trained on human and robot videoOriginal title: Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human ExperienceA preprint describes a world model that predicts loco-manipulation outcomes across humans and robots using shared kinematic conditioning.Added 9 Nov 2026
PreprintNot peer reviewedFrom Google / Google DeepMindArtificial IntelligenceResearchers report multi-agent system MaxKernel automates TPU kernel writingOriginal title: MaxKernel: Agentic Kernel Generation for TPUsA preprint describes MaxKernel, a multi-agent LLM system that writes and tunes TPU kernels, reporting speedups over compiler baselines.Added 9 Nov 2026
Journal articleReview status unknownFrom WelinqQuantum ComputingResearchers detail gate-reordering compiler to cut entanglement costs in distributed quantum computingOriginal title: Efficient Gate Reordering for Distributed Quantum Compiling in Data CentersThe authors describe araQne, a compiler that reorders quantum gates to reduce the entangled pairs needed across linked QPUs.Added 9 Nov 2026 · Released Dec 2025
PreprintNot peer reviewedArtificial IntelligenceResearchers report a multiscale method speeding up zeroth-order LLM fine-tuningOriginal title: ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-TuningA preprint introduces Engine, a zeroth-order fine-tuning method that mixes low- and full-dimensional updates for faster, more accurate LLM training.Zhuoli Ouyang et al. · Added 9 Nov 2026
