BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Yanbing Liu

Yanbing Liu appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
quant-phArtificial IntelligenceComputation and Languagecond-mat.mes-hallcond-mat.supr-conNetworking and Internet Architecturephysics.soc-phSocial and Information NetworksSoftware Engineering

Catalog footprint

What is connected

11works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

11 published item(s)

preprint2026arXiv

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering

Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforcement learning (RL) to end-to-end optimize the retrieval-augmented reasoning process, directly enhancing its capacity to resolve complex queries. However, reliable deployment is hindered by two obstacles. 1) Retrieval Collapse: iterative retrieval over large corpora fails to locate intermediate evidence containing bridge answers without reasoning-guided planning, causing downstream reasoning to collapse. 2) Learning Instability: end-to-end trajectory training suffers from weak credit assignment across reasoning chains and poor error localization across modules, causing overfitting to benchmark-specific heuristics that limit transferability and stability. To address these problems, we propose PRISMA, a decoupled RL-guided framework featuring a Plan-Retrieve-Inspect-Solve-Memoize architecture. PRISMA's strength lies in reasoning-guided collaboration: the Inspector provides reasoning-based feedback to refine the Planner's decomposition and fine-grained retrieval, while enforcing evidence-grounded reasoning in the Solver. We optimize individual agent capabilities via Two-Stage Group Relative Policy Optimization (GRPO). Stage I calibrates the Planner and Solver as specialized experts in planning and reasoning, while Stage II utilizes Observation-Aware Residual Policy Optimization (OARPO) to enhance the Inspector's ability to verify context and trigger targeted recovery. Experiments show that PRISMA achieves state-of-the-art performance on ten benchmarks and can be deployed efficiently in real-world scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

S^2tory: Story Spine Distillation for Movie Script Summarization

Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level saliency methods ineffective at preserving core story progression. To address this, we introduce S^2tory (Story Spine Distillation), a narratology-grounded framework that leverages character development trajectories to identify plot nuclei, the essential events that drive the narrative forward, while filtering out peripheral satellite events that merely enrich atmosphere or emotion. Our Narrative Expert Agent (NEAgent) performs theory-constrained reasoning, whose distilled knowledge conditions a small model to identify plot nuclei. Another model then uses these plot nuclei to generate the summary. Experiments on the MovieSum dataset demonstrate state-of-the-art semantic fidelity at approximately 3.5x compression, and zero-shot evaluation on BookSum confirms strong out-of-domain generalization. Human evaluation further validates that narratological theory provides an indispensable foundation for modeling complex, non-linear narratives.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

HaluNet: Multi-Granular Uncertainty Modeling for Efficient Hallucination Detection in LLM Question Answering

Large Language Models (LLMs) excel at question answering (QA) but often generate hallucinations, including factual errors or fabricated content. Detecting hallucinations from internal uncertainty signals is attractive due to its scalability and independence from external resources. Existing methods often aim to accurately capture a single type of uncertainty while overlooking the complementarity among different sources, particularly between token-level probability uncertainty and the uncertainty conveyed by internal semantic representations, which provide complementary views on model reliability. We present \textbf{HaluNet}, a lightweight and trainable neural framework that integrates multi granular token level uncertainties by combining semantic embeddings with probabilistic confidence and distributional uncertainty. Its multi branch architecture adaptively fuses what the model knows with the uncertainty expressed in its outputs, enabling efficient one pass hallucination detection. Experiments on SQuAD, TriviaQA, and Natural Questions show that HaluNet delivers strong detection performance and favorable computational efficiency, with or without access to context, highlighting its potential for real time hallucination detection in LLM based QA systems.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Quantum electrodynamics near a photonic band-gap

Photonic crystals provide an extremely powerful toolset for manipulation of optical dispersion and density of states, and have thus been employed for applications from photon generation to quantum sensing with NVs and atoms. The unique control afforded by these media make them a beautiful, if unexplored, playground for strong coupling quantum electrodynamics, where a single, highly nonlinear emitter hybridizes with the band structure of the crystal. In this work we demonstrate that such hybridization can create localized cavity modes that live within the photonic band-gap, whose localization and spectral properties we explore in detail. We then demonstrate that the coloured vacuum of the photonic crystal can be employed for efficient dissipative state preparation. This work opens exciting prospects for engineering long-range spin models in the circuit QED architecture, as well as new opportunities for dissipative quantum state engineering.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Beyond Strong Coupling in a Massively Multimode Cavity

The study of light-matter interaction has seen a resurgence in recent years, stimulated by highly controllable, precise, and modular experiments in cavity quantum electrodynamics (QED). The achievement of strong coupling, where the coupling between a single atom and fundamental cavity mode exceeds the decay rates, was a major milestone that opened the doors to a multitude of new investigations. Here we introduce multimode strong coupling (MMSC), where the coupling is comparable to the free spectral range (FSR) of the cavity, i.e. the rate at which a qubit can absorb a photon from the cavity is comparable to the round trip transit rate of a photon in the cavity. We realize, via the circuit QED architecture, the first experiment accessing the MMSC regime, and report remarkably widespread and structured resonance fluorescence, whose origin extends beyond cavity enhancement of sidebands. Our results capture complex multimode, multiphoton processes, and the emergence of ultranarrow linewidths. Beyond the novel phenomena presented here, MMSC opens a major new direction in the exploration of light-matter interactions.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Broadband Filters for Abatement of Spontaneous Emission in Circuit Quantum Electrodynamics

The ability to perform fast, high-fidelity readout of quantum bits (qubits) is essential to the goal of building a quantum computer. However, coupling a fast measurement channel to a superconducting qubit typically also speeds up its relaxation via spontaneous emission. Here we use impedance engineering to design a filter by which photons may easily leave the resonator at the cavity frequency but not at the qubit frequency. We implement this broadband filter in both an on-chip and off-chip configuration.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Integrated structure investigation in complex networks by label propagation

The investigation of network structure has important significance to understand the functions of various complex networks. The communities with hierarchical and overlapping structures and the special nodes like hubs and outliers are all common structure features to the networks. Network structure investigation has attracted considerable research effort recently. However, existing studies have only partially explored the structure features. In this paper, a label propagation based integrated network structure investigation algorithm (LINSIA) is proposed. The main novelty here is that LINSIA can uncover hierarchical and overlapping communities, as well as hubs and outliers. Moreover, LINSIA can provide insight into the label propagation mechanism and propose a parameter-free solution that requires no prior knowledge. In addition, LINSIA can give out a soft-partitioning result and depict the degree of overlapping nodes belonging to each relevant community. The proposed algorithm is validated on various synthetic and real-world networks. Experimental results demonstrate that the algorithm outperforms several state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

A Novel Admission Control Model in Cloud Computing

With the rapid development of Cloud computing technologies and wide adopt of Cloud services and applications, QoS provisioning in Clouds becomes an important research topic. In this paper, we propose an admission control mechanism for Cloud computing. In particular we consider the high volume of simultaneous requests for Cloud services and develop admission control for aggregated traffic flows to address this challenge. By employ network calculus, we determine effective bandwidth for aggregate flow, which is used for making admission control decision. In order to improve network resource allocation while achieving Cloud service QoS, we investigate the relationship between effective bandwidth and equivalent capacity. We have also conducted extensive experiments to evaluate performance of the proposed admission control mechanism.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

High fidelity single-shot readout of a transmon qubit using a SLUG μwave amplifier

We report high-fidelity, quantum nondemolition, single-shot readout of a superconducting transmon qubit using a DC-biased superconducting low-inductance undulatory galvanometer(SLUG) amplifier. The SLUG improves the system signal-to-noise ratio by 7 dB in a 20 MHz window compared with a bare HEMT amplifier. An optimal cavity drive pulse is chosen using a genetic search algorithm, leading to a maximum combined readout and preparation fidelity of 91.9% with a measurement time of Tmeas = 200ns. Using post-selection to remove preparation errors caused by heating, we realize a combined preparation and readout fidelity of 94.3%.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Time-Reversal Symmetrization of Spontaneous Emission for High Fidelity Quantum State Transfer

We demonstrate the ability to control the spontaneous emission from a superconducting qubit coupled to a cavity. The time domain profile of the emitted photon is shaped into a symmetric truncated exponential. The experiment is enabled by a qubit coupled to a cavity, with a coupling strength that can be tuned in tens of nanoseconds while maintaining a constant dressed state emission frequency. Symmetrization of the photonic wave packet will enable use of photons as flying qubits for transfering the quantum state between atoms in distant cavities.

0 citations0 reviewsNo code linkedOpen access