arXiv subjects

Zhenyu Li

Publications and source records attributed to Zhenyu Li.

At least 19 recordsLinked to original sources

arXiv2026

Arcturus: A Cloud Overlay Network for Global Accelerator with Enhanced Performance and Stability

Global Accelerator (GA) services play a vital role in ensuring low-latency, high-reliability communication for real-time interactive applications. However, existing GA offerings are tightly bound to specific cloud providers, resulting in high costs, rigid deployment, and limited flexibility, especially for large-scale or budget-sensitive deployments. Arcturus is a cloud-native GA framework that revisits the design of GA systems by leveraging low-cost, heterogeneous cloud resources across multiple providers. Rather than relying on fixed, high-end infrastructure, Arcturus dynamically constructs its acceleration network and balances performance, stability, and resource efficiency. To achieve this, Arcturus introduces a two-plane design: a forwarding plane that builds a proxy network with adaptive control, and a scheduling plane that coordinates load and routing through lightweight, quantitative optimization. Evaluations under millions of RPS show that Arcturus outperforms commercial GA services by up to 1.7X in acceleration performance, reduces cost by 71%, and maintains over 80% resource efficiency--demonstrating efficient use of cloud resources at scale.

cs.NI↗

arXiv2026

When "Must" Becomes "Maybe": Erosion of Workflow Constraints in LLM Agent Handoffs

Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downstream agent continue without revisiting the complete upstream context. We uncover a hidden loss in this process: handoffs can carry tasks forward while eroding judgments already established upstream. A requirement that must be satisfied before action becomes a caveat that the next agent may acknowledge and set aside. The issue remains visible, but its role has changed. We define operational state preservation as retaining an established judgment's role in constraining downstream action. Safety blockers provide a concrete instance: an unresolved prerequisite restricts the admissible actions until the condition is resolved. In our experiments, we confirm correct upstream detection, hold source permissions fixed, and vary the handoff supplied to a local-view executor. Direct-state controls preserve every blocker, whereas compression, plan assimilation, convergence, ownership deferral, and precedent substitution repeatedly weaken them. Ownership deferral produces 76.7% blocker deactivation; multihop compression produces 97.2%. Measuring the transmitted state separately from endpoint action exposes two routes to behavioral recovery. In fixed-artifact replays, restoring the full blocker description raises recognition from 6.2% to 99.2% and reduces forbidden action from 85.2% to 0.0%. An authorization-check prompt instead reduces forbidden action to 1.6% while leaving artifact deactivation at 95.3%. A successful endpoint can therefore conceal a damaged handoff. These findings make maintaining earlier judgments a core capability of reliable collaboration: each stage must carry forward both what earlier work established and what it requires of subsequent action. Semantic availability does not guarantee operational preservation.

cs.AI↗

arXiv2026

Development of a Minimal Auxiliary Basis for the Particle--Particle Random Phase Approximation (ppRPA): Accelerating Excited-State Calculations in Diradical Nanoparticles and Periodic Systems

Singlet--triplet gaps set the energy scale of the two-spin manifold in molecular quantum information materials, and such systems frequently carry diradical character: metal nanoclusters, metal--organic frameworks with radical linkers, and the nitrogen--vacancy center in diamond. Time-dependent density functional theory is the standard tool at this size but describes multireference systems poorly. A closed-shell reference is inadequate for a multiconfigurational ground state, and the adiabatic kernel excludes doubly excited configurations. The particle--particle random phase approximation (\pprpa{}) changes the particle number rather than the spin. Singlet and triplet states descend from one closed-shell reference, and double excitations enter on the same footing as single ones. Computational cost has confined \pprpa{} to small systems, and the two-electron integrals that drive it are factorized through an auxiliary basis. We develop \pprpa{}--as, which reduces that basis to a minimal set of atom-centered Gaussian shells whose exponents follow from free-atom radii and one global scaling factor. The approximation enters only the excited-state step, so both calculations proceed from the same self-consistent reference. We test molecules and clusters of up to 286 atoms, including heavy elements, and seven point defects in four periodic hosts, obtaining both multiplicities and their splitting without symmetry breaking or spin projection. We optimize the scaling factor and give guidance on choosing it. An order-of-magnitude smaller auxiliary basis delivers a speed-up of up to eightfold while staying within $0.03$~eV of conventional \pprpa{}, bringing diradical nanoclusters and periodic systems within reach.

physics.chem-ph↗

arXiv2026

Achieving room temperature plasticity in TiO2 ceramics by flash processing

Ceramics are indispensable materials for modern engineering and high-technology applications. However, the intrinsic brittleness at room temperature can cause catastrophic failure and severely limit their widespread applications. Here, we report a flash processing (FP) method based on the coupling of electric and thermal fields to significantly improve the room-temperature plasticity of TiO2 ceramics with a large plastic compressive strain of 15.4% during micropillar compression. This large room-temperature plasticity is attributed to the proliferation of stacking faults and twin boundaries during the loading process, which may be assisted by the high concentration of oxygen vacancies introduced by the FP method. Our findings suggest that FP can be a simple and effective method for achieving improved room-temperature plasticity of ceramic materials through defect engineering.

cond-mat.mtrl-sci↗

arXiv2026

Minimal building blocks for molecular quantum circuits with exact spin symmetry

Preserving particle number and spin helps quantum circuits target molecular electronic states, but does not guarantee access to every state with the required quantum numbers. We determine which additional operations, combined with spin-independent orbital rotations connecting all spatial orbitals, generate every real state-space rotation within each complete subspace of fixed particle number $N$, total spin $S$, and spin projection $M_S$. We consider spin-free molecular calculations in real orbitals, without an additional spatial-symmetry restriction, and continuously tunable operations that preserve particle number, full spin symmetry, and real amplitudes. Below the maximal-spin limits set by the electron and hole numbers, repeated singlet-pair transfer between any two fixed spatial orbitals is sufficient. On nontrivial maximal-spin boundaries, pair transfer vanishes, and an additional generator built from one- and two-electron terms is sufficient exactly when its action in the target subspace is not a linear combination of orbital-rotation generators. The minimum number of spatial orbitals needed by one additional generator is two in the interior and three on nontrivial boundaries, even when terms involving more than two electrons are allowed. Both minima are attained using only one- and two-electron terms. The three-orbital optimum rotates two orbitals according to the occupation of a third, and its unitary factors exactly into eight commuting Pauli rotations. Molecular benchmarks show that this operation removes the observed boundary energy-error plateaus, while sparse interior constructions attain the prescribed energy accuracy with fewer compiled CNOT gates in selected fixed-orbital comparisons.

quant-ph↗

arXiv2026

X-MoD: Practical Scaling Laws for Sparse-Depth Routing Beyond Mixture-of-Depths

Mixture-of-Depths (MoD) enables conditional computation across Transformer depth by routing only a subset of tokens through selected layers, but its original one-sparse--one-dense alternation tightly couples total capacity to active capacity and limits sparse-depth scaling. We introduce X-MoD, a scalable sparse-depth architecture that decouples token sparsity from anchor stride, allowing total parameter count to grow while keeping active-equivalent capacity nearly fixed. To make deep sparse routing trainable, X-MoD combines dense anchors with variance-scaled layer-wise gating and depth-wise token balancing. To make this regime analyzable and usable, we formulate sparse-depth routing as a conditional architecture-design problem: given compute, context length, and active-equivalent backbone size, how should the routing configuration be chosen? We develop a practical scaling-law framework by fitting X-MoD relative to FLOP-matched dense baselines, yielding an interpretable law that decomposes performance into sparse-capacity gain, sparse-context correction, and anchor-stride interaction. The law predicts validation loss across routing configurations and reveals how context length, model scale, and anchor stride shape sparse-depth performance. We validate the architecture and law through pretraining sweeps, held-out scaling-law prediction, ablations, downstream evaluations, and comparisons with Dense, MoD, and representative MoE baselines.

cs.LG↗

arXiv2026

PosEviLoc: Position-Conditioned Spatial Evidence for Language-Based 3D Localization

Language-based 3D localization retrieves the point-cloud submap containing a target position from descriptions of nearby objects and their spatial relations. Existing methods typically compress queries and submaps into global descriptors, potentially obscuring object-level semantics and cross-description spatial coherence. We propose Position-Conditioned Evidence Localization (PosEviLoc), a query-position-aware framework for coarse text-to-point-cloud localization. Instead of relying on global matching, PosEviLoc evaluates each candidate submap using explicit semantic and spatial evidence. It models direction as a relation jointly determined by an object position and a hypothetical query position. The resulting Query-Position Spatial Evidence Field (QSEF) measures the fraction of query descriptions supported at each hypothetical position, explicitly capturing their agreement without using the ground-truth query pose to construct the evidence field. A Multi-Level Evidence Readout (MER) summarizes this evidence in a compact representation, which a lightweight MLP converts into a retrieval score. Across five benchmarks, PosEviLoc outperforms MNCL by an average of 17 percentage points in Recall@1. When used as a plug-and-play reranker, it improves MNCL by an average of 16 percentage points. Moreover, PosEviLoc introduces substantially fewer parameters and achieves faster inference speed than existing methods.

cs.CV↗

arXiv2026

Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning

Reconstructing articulated objects from sparse images requires recovering complete geometry, movable parts, and motion parameters. Recent methods typically separate geometry reconstruction, part reasoning, and articulation estimation into different stages. This separation can weaken consistency between shape, active parts, and motion, while also incurring substantial inference cost. We introduce Artic-O, an end-to-end, feed-forward framework for articulated object reconstruction via latent geometry learning. Instead of fitting geometry in image or view space, Artic-O maps sparse multi-state observations into a pretrained latent geometry space, where a frozen flow-matching decoder provides a complete-shape prior for recovering visible and occluded structures. To connect geometry with articulation, Artic-O fuses visual tokens, geometry latents, and point-wise decoder features in an image-grounded part-reasoning module for active-part segmentation and articulation prediction. We further train the model with a geometry-to-articulation curriculum and a decoupled two-pass strategy to balance reconstruction and part-level supervision. On PartNet-Mobility, Artic-O achieves strong reconstruction quality while being substantially more efficient than LARM, a strong prior method. It reduces Chamfer Distance, improves F-score, and achieves comparable or better articulation accuracy across most joint metrics, while reducing inference time from 9 minutes to about 0.3 seconds per object.

cs.CV↗

arXiv2026

Perturbative Variational Quantum Eigensolver via Reduced Density Matrices

Current noisy intermediate-scale quantum (NISQ) devices remain limited in their ability to perform accurate quantum chemistry simulations due to restricted numbers of high-fidelity qubits and short coherence times. To overcome these challenges, we introduce a reduced density matrix (RDM)-based perturbative variational quantum eigensolver (VQE) framework that augments active-space VQE with perturbation theory to recover electron correlation beyond the active space without increasing the qubit count or variational circuit depth. We formulate a fully coupled approach (VQE-PTs) and a diagonal approximation (VQE-PT). The former retains couplings among orthonormalized perturbers, whereas the latter neglects these couplings to simplify the classical post-processing. Numerical simulations of HF, N$_2$, and F$_2$ show that VQE-PTs provides a robust formulation across different molecular systems, while VQE-PT offers an efficient approximation. We further experimentally implement VQE-PT on the Quafu superconducting quantum processor for F$_2$, achieving a mean absolute error of 1.2 millihartree along the potential energy surface after error mitigation. These results demonstrate perturbative VQE as a practical framework for incorporating dynamic correlation in quantum chemistry simulations.

quant-ph↗

arXiv2026

TurboRetry: Mitigating Large-Scale QUIC Handshake Floods with Off-the-Shelf DPU Offloading

The modern transport protocol QUIC is designed to enhance network performance and security, but it remains vulnerable to handshake flooding attacks. Such attacks exhaust CPU resources by forcing the server to perform expensive cryptographic operations via a large number of handshaking requests. QUIC provides a built-in defense mechanism, the Retry mechanism, to mitigate these attacks. However, our experiments reveal that it can still become a performance bottleneck under large-scale QUIC handshake floods due to substantial computational overhead. In this paper, we design and implement TurboRetry, a split design, that offloads the Retry mechanism onto DPUs to efficiently mitigate QUIC handshake floods. TurboRetry partitions the tasks of the Retry into two categories, and then assigns them to the DPUs and the host, respectively. To preserve QUIC semantics and reduce the coordination overhead, TurboRetry designs an extended Retry token format and an efficient cooperation scheme. In addition, TurboRetry offloads the connection authorization task to the on-path DPA to further improve both performance and security. Our evaluation shows that TurboRetry outperforms the host-side implementation by a wide margin, improving throughput by 10-20$\times$.

cs.CR↗

arXiv2026

Embedded quantum computing for many-body surface reaction

Predictive simulations of catalytic interfaces require correlated electronic-structure treatments that describe localized chemical transformations while retaining the influence of the extended metallic environment. We introduce QC-DFET, a quantum-computing density-functional embedding framework that maps surface-reaction active spaces to compact, environment-aware qubit Hamiltonians. A reaction-consistent active-space protocol preserves orbital continuity along reaction coordinates, while quantum-selected configuration interaction based on measurements from the Zuchongzhi superconducting quantum processor and strongly contracted perturbation theory capture static and dynamic correlation. On Cu(111), QC-DFET treats active spaces up to 28 qubits and is validated through a hierarchy of experimentally constrained surface-chemistry challenges. H2 dissociation/desorption tests balanced bond breaking and recombination barriers, CO adsorption tests site selectivity and metal-adsorbate bonding, and formate hydrogenation tests competing hydrogenation branches with different kinetic and thermodynamic signatures. Across these cases, QC-DFET reproduces bidirectional H2 barriers, recovers the observed top-site preference and adsorption strength of CO, and reconciles the experimentally benchmarked H2COO* reverse barrier with the lower forward barrier to HCOOH*. These results establish embedded quantum computing as a practical route to correlated surface-reaction energetics.

quant-ph↗

arXiv2026

A High-Performance Pauli-Algebra Framework for Large-Scale Quantum Simulations

Efficient manipulation of Pauli-algebraic objects is a key bottleneck in the classical emulation and benchmarking of quantum algorithms for chemistry and many-body physics. This bottleneck appears in Hamiltonian construction, variational ansatz preparation, expectation-value and gradient evaluation, and real-time propagation, all of which require repeated Pauli-algebra operations. Here, we present a high-performance Pauli-algebra framework tailored to quantum many-body and quantum-chemical simulations. The framework combines compact binary symplectic encoding, canonical coefficient reduction, and grouped sparse operator representations that exploit shared bit-flip patterns among Pauli strings. The resulting Julia/C\texttt{++} implementation accelerates Pauli multiplication, Hamiltonian construction, and operator--state multiplication in sparse and symmetry-adapted many-electron spaces. Benchmarks demonstrate efficient Hamiltonian construction, large-active-space VQE and ADAPT-VQE calculations, and real-time variational dynamics on modern multicore CPU and GPU architectures. These results show that structure-aware Pauli-algebra engines provide a scalable classical backend for developing and benchmarking quantum algorithms in quantum chemistry and many-body simulation.

quant-ph↗

arXiv2026

False Positives Raised by Quantum Readout Error Mitigation

Quantum readout error mitigation is essential for noisy intermediate-scale quantum devices to achieve reliable data. The conventional approaches, conflating initialization errors with measurement errors, not only suppress the influence of measurement errors, but also strengthen that of initialization errors, which is a systematic bias grows exponentially with the qubit number. Here, we have proved that this effect causes severe fidelity overestimation for all stabilizer states and might lead to false positives in large-scale entangled state characterization. Similarly, the results from algorithms like the variational quantum eigensolver and time evolution also deviate negatively, and cover up other errors in the quantum circuit. These findings highlight the critical need for rigorous benchmarking and careful management of initialization errors. Consequently, we establish an upper bound for the tolerable initialization error rate to ensure effective error mitigation at a given system scale.

quant-ph↗

arXiv2026

CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging

Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness. While rubric-based LLM judges improve interpretability by decomposing evaluation into explicit criteria, most existing pipelines remain pointwise: they score each response independently and derive preferences by comparing aggregated scores. We show that this design is poorly matched to pairwise code preference prediction and can underperform a strong monolithic judge. We propose CriterAlign, a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation through direct criterion-level pairwise judgments, tie-driven criterion refinement, swap-consistency filtering, and final pairwise synthesis. We further introduce Human-Preference-Aligned Guidance (HPAG), synthesized offline from training examples by extracting recurring rationale gaps between human preferences and monolithic judge predictions, and injected into the criterion generator, criterion judge, and final judge. On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy, with ablations confirming the contributions of pairwise criterion design and HPAG.

cs.SE↗

arXiv2026

Physically Motivated Ansatz for Open Fermionic Systems on Quantum Computer

Determining non-equilibrium steady states (NESS) of open fermionic systems is a fundamental problem akin to finding ground states of closed systems. To address this, variational quantum algorithms can be used to solve the Lindblad master equation, much like the Schrödinger equation, yet ansatz design for NESS remains challenging. Existing approaches rely mostly on hardware-efficient ansätze (HEA), which suffer from the barren plateau problem. Here, we introduce a physically motivated ansatz named NE-UCC. Numerical simulations demonstrate that NE-UCC reliably converges to the steady state even in strongly correlated regimes far from equilibrium, reducing the infidelity by up to ten orders of magnitude compared to HEA. Furthermore, NE-UCC facilitates the exploration of excited eigenmodes with specific symmetries.

quant-ph↗

arXiv2026

Improved time-translationally invariant tensor network influence functional method for Anderson impurity problems

The Anderson impurity model (AIM) is of fundamental importance in condensed matter physics for studying strongly correlated phenomena. However, accurately simulating its long-time dynamics still remains a significant numerical challenge. A class of recently developed numerical approaches represents the Feynman-Vernon influence functional (IF), which encodes all the bath effects on the impurity, as a matrix product state (MPS) in the temporal domain. The computational cost of this approach is largely determined by the bond dimension $χ$ of the temporal MPS. In this work, we propose an efficient and accurate method that, when the hybridization function in the IF can be approximated as a sum of $n$ exponential functions, systematically constructs the IF as an MPS by multiplying $O(n)$ small MPSs, each with bond dimension $2$. Our method yields a worst case scaling of $χ$ as $2^{8n}$ and $2^{2n}$ for real- and imaginary-time evolution respectively. We demonstrate the performance of our method for two commonly used bath spectral functions, and show that the required bond dimensions are significantly smaller than the worst case.

cond-mat.str-el↗

arXiv2026

Quantum key distribution without authentication and information leakage

Quantum key distribution (QKD) is the most extensively researched quantum cryptographic protocol, leveraging quantum phenomena to enable information-theoretically secure key establishment. Conventional QKD systems rely on authenticated classical post-processing channels to prevent impersonation attacks. However, QKD inherently lacks authentication capabilities, necessitating an external authentication mechanism. Furthermore, the classical post-processing steps introduce information leakage, exposing QKD to additional attack strategies and diminishing the final key rate. In this study, we introduce a novel QKD protocol that eliminates the need for separate authentication, prevents information leakage, and significantly improves the achievable key rate. By removing public classical channels entirely, our design attains perfect secrecy with the use of two reusable pre-shared keys.

quant-ph↗

arXiv2026

DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation

Subject-driven image generation faces an "Identity-Diversity Paradox", where strong identity preservation often leads to rigid and low-diversity outputs. We propose a post-training framework called DivRL that jointly optimizes identity consistency and structural diversity simultaneously by leveraging disentangled visual features from a robust similarity model. Specifically, we introduce a Negative Self-Similarity Measure (nSSM) to quantify structural diversity, and Visual Semantic Matching (VSM) to evaluate identity consistency. We propose an "Explore-and-Suppress" strategy that treats VSM as a gated constraint: the model freely explores structurally diverse configurations, and only samples that violate the identity threshold are penalized via a quadratic hinge loss. This converts identity preservation from a competing objective into a feasibility constraint, allowing nSSM and VSM to improve jointly. Experiments demonstrate that our method effectively pushes the model to generate both consistent and diverse images and improves structural diversity while maintaining comparable identity consistency through a gated optimization formulation.

cs.CV↗