PreprintNot peer reviewedFrom AIM IntelligenceArtificial IntelligenceNew benchmark probes why multimodal AI models hallucinate across multiple imagesOriginal title: Fine-Grained Multi Image Object Hallucination BenchmarkA preprint introduces MIOH, a benchmark testing 29 models to find out where multi-image object hallucination actually originates.Added 18 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports a faster, exact simulator for non-Pauli noise in quantum error correctionOriginal title: Scalable Exact Non-Pauli Noise Simulation for Fault-Tolerant Quantum CircuitsA preprint presents QuasiStim, which simulates realistic quantum noise exactly, faster than tableau methods and without Pauli-twirl bias.Yuewen Hou et al. · Added 18 Oct 2026
Journal articleReview status unknownQuantum ComputingTrapped-ion setup reported to emit single photons with very low multi-photon rateOriginal title: Pure single photons from a trapped atom sourceResearchers report a trapped-ion photon source producing single photons at 200 kHz with a very low multi-photon component.Daniel B. Higginbottom et al. · Added 18 Oct 2026 · Released May 2016
Journal articleReview status unknownQuantum ComputingA preprint reports a cryogenic chip design to control many qubits with one microwave cableOriginal title: Cryogenic Multiplexing Control Chip for Superconducting Quantum ProcessorA preprint proposes a cryogenic chip that multiplexes microwave control signals to reduce wiring for superconducting quantum processors.Rutian Huang et al. · Added 18 Oct 2026 · Released Dec 2022
PreprintNot peer reviewedFrom Palo Alto NetworksArtificial IntelligenceA preprint reports bug-fixing benchmarks may be inflated by training data contaminationOriginal title: BenchChecker: Assessing the Credibility of Bug-Fixing Benchmarks for LLMsA preprint presents BenchChecker, a tool that detects contaminated test samples in LLM bug-fixing benchmarks using only text outputs.Added 18 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports a debugging framework for fault-tolerant quantum programsOriginal title: SynDebug: A Framework to Debug Logic Bugs in Fault-Tolerant Quantum Computing ProgramsResearchers describe SynDebug, a system-level assertion framework for spotting logic bugs in fault-tolerant quantum code with little overhead.Nicholas S. DiBrita et al. · Added 18 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceReview maps 114 studies on LLM-based multi-agent code generation systemsOriginal title: LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature ReviewA literature review pulls together academic and industry work on multi-agent LLM systems for code generation, covering benchmarks, challenges and open questions.Zeeshan Rasheeda et al. · Added 18 Oct 2026 · Released Feb 2026
Journal article✓ Peer reviewedQuantum ComputingProtocols aim to split quantum simulation workloads across linked quantum processorsOriginal title: Distributed Quantum SimulationA peer-reviewed study proposes ways to share quantum simulation tasks across networked quantum processors with less communication overhead.Tianfeng Feng et al. · Added 18 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint describes a multi-agent system that auto-converts jailbreak papers into runnable attack codeOriginal title: Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible BenchmarkingResearchers report an automated pipeline that turns jailbreak attack papers into executable, benchmark-ready modules with close fidelity to original results.Zhicheng Fang et al. · Added 18 Oct 2026 · Released Jul 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports a prompt-aware tuning method that beats LoRA with fewer bottlenecksOriginal title: PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdificationA preprint describes PEDRO, a parameter-efficient fine-tuning method that the authors say outperforms LoRA-style baselines while running faster in multi-tenant settings.Tianfang Xie et al. · Added 18 Oct 2026 · Released Sep 2024
Conference paperReview status unknownFrom GoogleArtificial IntelligenceResearchers detail Google’s PLUM framework for LLM-based YouTube recommendationsOriginal title: PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative RecommendationsA conference paper describes PLUM, which adapts pre-trained language models to generate video recommendations for YouTube, replacing large embedding tables.Added 18 Oct 2026 · Released Oct 2025
Conference paperReview status unknownArtificial IntelligenceResearchers combine LLM task planning and reward shaping for sparse-reward robot controlOriginal title: Progress Reward Model for Reinforcement Learning via Large Language ModelsA conference paper describes a framework that uses large language models to both plan subtasks and build dense rewards for reinforcement learning on robotics tasks.Xiuhui Zhang et al. · Added 18 Oct 2026 · Released Jan 2025
PreprintNot peer reviewedFrom MicrosoftQuantum ComputingA preprint maps instruction-set tradeoffs for scaling fault-tolerant quantum control hardwareOriginal title: Architecting Instruction Execution for Scalable Fault-Tolerant Quantum ComputingA preprint proposes a five-level quantum instruction set hierarchy and finds a mid-level design balances bandwidth, power and runtime for fault-tolerant quantum computers.Added 18 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports LLM agents inventing their own symbolic languages to reason fasterOriginal title: When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent ReasoningA preprint describes LLM agents that evolve shared symbolic shorthand protocols, cutting reasoning tokens while keeping accuracy steady.Zhengqi Pei et al. · Added 18 Oct 2026
PreprintNot peer reviewedFrom Western DigitalArtificial IntelligenceA preprint reports a mobile KV-cache system that extends on-device LLM context lengthOriginal title: TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV CachingA preprint describes TierKV, a mobile LLM inference system that predicts and tiers KV-cache storage to support longer contexts on phones.Added 18 Oct 2026
PreprintNot peer reviewedFrom TencentArtificial IntelligenceResearchers report long-context LLMs often fail to spot unanswerable questionsOriginal title: Towards Reliable Long-Context Reasoning: Detecting Unanswerable Questions via FactGuardA preprint introduces a benchmark and training method to help long-context language models recognise when a question cannot be answered from the given text.Added 18 Oct 2026
Journal articleReview status unknownFrom Quantum MotionQuantum ComputingStudy weighs catalyst towers against standard synthesis for surface-code rotationsOriginal title: Space and Time Cost of Continuous Rotations in Surface CodesThe authors examine whether catalyst towers reduce runtime and space costs for continuous rotation gates in surface codes.Added 18 Oct 2026 · Released Aug 2025
Journal article✓ Peer reviewedQuantum ComputingSuperconducting circuits fuse photonic cluster states into 13-qubit entangled graphsOriginal title: Deterministic and Programmable Fusion for Scalable Generation of Photonic Graph StatesResearchers report a deterministic fusion method that joins small photonic cluster states into larger programmable graph states using superconducting circuits.Yan Li et al. · Added 18 Oct 2026
PreprintNot peer reviewedFrom QuEra ComputingQuantum ComputingPreprint describes PPVM, a simulation framework for digital twin quantum processorsOriginal title: PPVM: A Circuit Simulation Framework for Digital Twins of Quantum ProcessorsA preprint introduces PPVM, an open-source virtual machine that jointly simulates quantum hardware, noise and classical control for digital twins of quantum processors.Added 18 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint traces PPO training collapses to critic instability and proposes fixesOriginal title: EasyPPO: Stabilizing the Critic Is KeyA preprint reports that two critic failure modes destabilise PPO for LLM reasoning, and proposes EasyPPO to fix them.Xuanyi Zhou et al. · Added 18 Oct 2026
