arXiv subjects

Jie Meng

Publications and source records attributed to Jie Meng.

At least 19 recordsLinked to original sources

arXiv2026

CCAaaS: An Orchestration Platform for High-Velocity Design, Development, and Deployment of Data Center Transports at Meta

Today, data center networks run multiple congestion control algorithms (CCAs), each tailored to distinct traffic characteristics, from latency-sensitive intra-region RPCs to high-throughput cross-region AI workloads. The rapid evolution of AI training and inference further accelerates this trend by continually introducing new traffic characteristics that demand new CCAs. This paper introduces CCA-as-a-Service (CCAaaS), our eBPF-based ecosystem for the rapid design, deployment, and operation of production-grade CCAs at hyperscale. We present (1) a modular BPF-TCP framework and general lessons for designing modular CCAs; (2) a deployment and orchestration layer that provides disruption-free CCA updates, along with best practices for managing a zoo of CCAs at scale; and (3) a lightweight observability tool for CCAs and a blueprint for scaling CCA observability. CCAaaS manages over 97% of our server-to-server traffic using three active eBPF-based CCAs; two of the five CCAs we have built have since been deprecated. We show that our eBPF-centric approach to CCAs development delivers the same application-level performance (retransmissions, bandwidth, and tail latency) as their native in-kernel counterparts, and that our custom CCAs add negligible CPU and memory cost over their eBPF baselines. In terms of realized benefits, the CCA built with CCAaaS significantly improved network, and application metrics, for example, one of our CCAs reduced P99 latency for cross-region services by up to 20X.

cs.NI↗

arXiv2026

From ASIC to Fleet: Lessons from Building and Operating a Hyperscaler NIC

We describe the operational infrastructure built to deploy and operate fbnic, a custom multi-host NIC, across hundreds of thousands of production hosts at Meta. Vendor multi-host NICs, designed by retrofitting single-host architectures, suffered from shared firmware and buffers that created cascading isolation failures over seven years. fbnic eliminates these through physical isolation, but shifting to in-house hardware shifts the entire operational burden to the hyperscaler. We present a hardware-in-the-loop CI pipeline testing firmware, driver, and kernel cross-products; a unified observability pipeline co-locating NIC and switch counters for cross-layer fault attribution; a driver-first architecture with fewer than ten firmware message types; a targeted firmware upgrade orchestrator at sub-sled granularity; and scoped repair automation confining blast radius to individual host slices. Over ten months, fbnic achieved a 12X reduction in unplanned unavailability, 37% lower mean time to repair, and 2.3X fewer hardware swaps compared to vendor NICs on the same platform.

cs.NI↗

arXiv2026

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, III: nuclei with $8 \leq Z \leq 120$

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for nuclei with $8 \leq Z \leq 120$, extended from the previous works for even-even nuclei [Zhang et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)] and for even-$Z$ nuclei [Guo et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 158, 101661 (2024)]. The calculated binding energies, two- and one-nucleon separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, neutron and proton Fermi surfaces, and the blocked neutron (proton) orbitals of odd-$N$ ($Z$) nuclei are tabulated and compared with the available experimental data. A total of 9495 nuclei are predicted to be bound, with an rms deviation of 1.444 MeV from the 2380 mass data. Good agreement with the available experimental pairing gaps, $α$ decay energies, and charge radii is also achieved. The accuracies of the calculated nuclear masses and nucleon separation energies as well as the prediction for drip lines are compared with those obtained by other relativistic and nonrelativistic density functional calculations. It turns out that the DRHBc theory with PC-PK1 provides one of the best microscopic descriptions for nuclear masses. The systematics of nucleon separation energies, pairing gaps, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗

arXiv2026

MoE-CORE: Coordinated Expert Offloading and Residency for Memory-Constrained MoE Inference

Sparse expert activation reduces MoE models' computation, yet expert weights can exceed limited device memory. Offloading makes inference feasible on a compact AI appliance but exposes host-to-device transfers to the inference path. We present MoE-CORE, a system that coordinates expert offloading and residency for memory-constrained MoE inference. It stages complete expert layers in alternating buffers during prefill. During decode, it combines nonuniform layer-wise cache capacity, domain-informed initialization, routing-history-aware replacement, and cross-layer prefetching. The main configuration executes router-selected experts exactly; an optional score-based substitution path handles eligible low-score misses. The main comparison uses 1K- and 128-token output caps for MoE-CORE and vLLM Prefetch, respectively. Across five workloads per model, MoE-CORE records a mean time per output token (TPOT) of 38.0-44.8 ms versus 1268.9-1269.1 ms for the evaluated vLLM Prefetch configuration on DeepSeek-V4-Flash-W4A8; the corresponding values on GLM-5.2-W4A8C8 are 206.6-220.5 and 5941.5-5941.8 ms. Under an 84-GB NPU-memory cap, the best measured DeepSeek GSM8K configuration achieves a TPOT of 21.5 ms with approximate expert substitution and multi-token prediction (MTP) at depth 2. These results support coordinated expert residency and transfer scheduling under a device-memory constraint. The code is here.

cs.DC↗

arXiv2026

RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning

Multimodal reasoning requires models to preserve visual evidence through long decision chains while selecting appropriate procedures across diverse scenarios and rules. When learning is guided only by terminal verifiers, reinforcement learning (RL) reveals whether a final answer is correct but not how it should be produced. The policy must therefore discover reusable reasoning procedures while learning to execute them, creating a program cold-start problem. Skills can externalize successful procedures, reduce repeated exploration, and provide inspectable guidance. However, a fixed Skill Bank assumes that this guidance remains compatible with an evolving policy, while updating Skills alone can leave their triggers, execution protocols, and demonstrations stale or mutually inconsistent. We introduce RLHARNESS, which organizes Skills, selection and execution protocols, few-shot demonstrations, and task contracts into a unified, versioned Harness and alternates Harness evolution with policy learning. An Exploration-Distillation Harness builds the initial Harness and version-aligned verified traces for SFT and DAPO I. After the first RL block, a Post-RL Reconstruction Harness rebuilds Skills, protocols, and demonstrations from fresh success-failure rollouts, and DAPO II adapts the policy to the reconstructed program. RLHARNESS improves Accuracy from 16.25%/27.50% to 62.00%/50.00% on MetroMap/TravelMap and raises F1 score from 37.13%/45.50% to 65.81%/65.51% on Fee-VL/Cancel-VL. All four tasks achieve their best results only after reconstruction and DAPO II, showing that an evolving Harness complements RL by continually updating the external program that the policy learns to execute.

cs.AI↗

arXiv2026

Pairing correlations, orientations and quantum fluctuations in one- and two-nucleon transfer reactions at sub-barrier energies

This work investigates one- and two-neutron transfer in the $^{96}\text{Zr} + {}^{40}\text{Ca}$ reaction at sub-barrier energies using a microscopic framework based on time-dependent covariant density functional theory (TD-CDFT). Pairing correlations are incorporated via the time-dependent BCS approximation, which is shown to significantly enhance pair transfer, as evidenced by an increased two-neutron transfer probability. The oblate deformation of $^{96}$Zr causes the transfer probabilities to vary by orders of magnitude with orientation; a direct comparison with experiment is enabled by averaging results over thirteen systematically chosen orientations. While the orientation-averaged one-neutron transfer probabilities agree well with data, the two-neutron channel is suppressed below the Coulomb barrier. This suppression is attributed to missing quantum fluctuations in the semiclassical TD-CDFT approach. To test this, we employ the generalized time-dependent generator coordinate method (TDGCM), which confirms that quantum fluctuations are essential for an accurate description of sub-barrier two-neutron transfer dynamics.

nucl-th↗

arXiv2026

Component-wise accurate fixed point iterations for computing the square root of a singular M-matrix

We analyze two fixed-point iterations for computing the principal square root of an M-matrix $A$. Although these iterations, with customary initialization, converge sublinearly when $A$ is a singular M-matrix, we show that, under suitable mild conditions on the initial approximation, the convergence is linear. Moreover, we provide component-wise accurate versions of these iterations, which allow us to approximate the principal square root with a component-wise relative error uniformly bounded by a small multiple of the machine precision. Numerical experiments demonstrating the effectiveness of the proposed algorithms for certain classes of problems are presented.

math.NA↗

arXiv2026

SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings

Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Subset Simulation (SS) addresses this by decomposing a rare-event probability into moderate conditional probabilities over nested intermediate events. However, classical SS requires a handcrafted scalar performance function whose sublevel sets define those events, demanding detailed knowledge of the failure geometry and limiting transfer to new domains. We propose SCARCE (Scalable Cascade Analysis for Rare-event Characterisation via Embeddings), which replaces the performance function with learned latent representations and geometric rulers that score proximity to failure regions. Adaptive thresholding constructs nested intermediate events directly from data. We formalise SCARCE through a non-negative supermartingale, yielding a high-probability upper envelope that remains valid under early stopping. On MNIST misclassification, where dense Monte Carlo provides ground truth, SCARCE achieves approximately 400--500 times lower mean absolute error than grid-searched traditional SS while eliminating systematic over-counting. We then study PAIR-style LLM jailbreaks under a fleet-level threat model with adversarial fraction $η$. On Llama-Guard-3-8B hidden states, a PCA-based ruler attains 2.6% mean relative error for $η\geq 10^{-3}$ against finite-sample references whose average bootstrap relative half-width is 27.9%, and transfers to a GCG-style corpus with 2.93% relative error after recalibration. A directional criterion $\mathrm{KL}(p_{\mathrm{good}}\,\|\,p_{\mathrm{bad}})$ ranks rulers consistently with estimation error (Spearman $ρ=0.83$).

cs.AI↗

arXiv2026

Component-wise accurate computation of the square root of an M-matrix

Component-wise accurate algorithms for computing the principal square root of an M-matrix are designed in terms of triplet representations. A triplet representation of an M-matrix $A$ is the triple $(P, {\bf u},{\bf v})$, where the matrix $P$ is such that $p_{ij}=-a_{ij}$ for $i\ne j$, $p_{ii}=0$, and ${\bf u}>0$, ${\bf v}\ge 0$ are two vectors such that $A{\bf u}={\bf v}$. It is shown that if $A$ is an M-matrix representable by a triplet, then its principal square root exists and is an M-matrix represented by a triplet as well. New versions of the Cyclic Reduction and the Incremental Newton iterations are provided in terms of triplets, to compute the principal matrix square root of $A$. It is shown that these algorithms are component-wise numerically stable independently of the singularity of $A$ and of its condition number. Numerical experiments are shown to confirm the component-wise stability.

math.NA↗

arXiv2026

Theoretical analysis and numerical solution to a vector equation $Ax-\|x\|_1x=b$

Theoretical and computational properties of a vector equation $Ax-\|x\|_1x=b$ are investigated, where $A$ is an invertible $M$-matrix and $b$ is a nonnegative vector. Existence and uniqueness of a nonnegative solution is proved. Fixed-point iterations, including a relaxed fixed-point iteration and Newton iteration, are proposed and analyzed. A structure-preserving doubling algorithm is proved to be applicable in computing the required solution, the convergence is at least linear with rate 1/2. Numerical experiments are performed to demonstrate the effectiveness of the proposed algorithms.

math.NA↗

arXiv2026

A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication

The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairness. However, the exponential surge in ride-hailing volume renders manual review intractable, while conventional automated methods lack the reasoning transparency required for quasi-judicial decisions. Although Multimodal LLMs offer a promising paradigm, they fundamentally struggle to bridge the gap between general visual semantics and rigorous evidentiary protocols, often leading to perceptual hallucinations and logical looseness. To address these systemic misalignments, we introduce RideJudge, a Progressive Visual-Logic-Aligned Framework. Instead of relying on generic pre-training, we bridge the semantic gap via SynTraj, a synthesis engine that grounds abstract liability concepts into concrete trajectory patterns. To resolve the conflict between massive regulation volume and limited context windows, we propose an Adaptive Context Optimization strategy that distills expert knowledge, coupled with a Chain-of-Adjudication mechanism to enforce active evidentiary inquiry. Furthermore, addressing the inadequacy of sparse binary feedback for complex liability assessment, we implement a novel Ordinal-Sensitive Reinforcement Learning mechanism that calibrates decision boundaries against hierarchical severity. Extensive experiments show that our RideJudge-8B achieves 88.41\% accuracy, surpassing 32B-scale baselines and establishing a new standard for interpretable adjudication.

cs.AI↗

arXiv2026

Unstable Slip in Fault Gouge Driven by Temperature and Water

Microscale granular sliding within fault gouge is fundamental to earthquake nucleation, yet the mechanism by which temperature affects friction through interfacial water remains poorly understood. Here, large-scale molecular dynamics simulations were conducted on a hydrophilic quartz-water-quartz interface over 300-500 K to quantify temperature-dependent changes in frictional strength, real contact area, and water-layer structure. Results show that both the friction coefficient and friction force decrease monotonically with increasing temperature, following near-linear relationships of $μ\propto T^{-1}$ and $F_t \propto A$, indicating that frictional weakening is primarily governed by temperature-driven contact restructuring. Structural analyses further show that heating progressively disrupts the hydrogen-bond network in the first adsorption layer, reduces adsorption-layer density, and weakens radial distribution peaks, demonstrating a transition of interfacial water from an ordered, strongly adsorbed state to a more diffuse, weakly bound configuration with delayering and quasi-phase-transition behavior. This interfacial reconstruction weakens intergranular bridging and structural cohesion, promoting a shift from structural locking to water-mediated lubrication. These results suggest that frictional stability under coupled temperature-water conditions is strongly controlled by the thermal evolution of interfacial water structure.

physics.geo-ph↗

arXiv2026

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentralized serving. This report presents xDeepServe, the production serving system behind Huawei Cloud's MaaS offering on CloudMatrix384, a 48-server SuperPod with 384 Ascend 910C chips connected by a high-bandwidth UB fabric and global shared memory. It serves models including DeepSeek, Kimi, GLM, Qwen, and MiniMax, among others. xDeepServe is built around Transformerless, a disaggregated execution architecture that decomposes transformer inference into modular units -- attention, feedforward, and MoE -- and supports disaggregated Prefill-Decode and MoE-Attention deployments. To enable disaggregation, we develop XCCL, a memory-semantic communication layer providing microsecond-level point-to-point and scalable all-to-all primitives, and we extend FlowServe with decentralized DP groups and techniques to mitigate stragglers and synchronization variance. In a peak decoding configuration, xDeepServe reaches 2400 tokens/s per Ascend 910C chip at ~50ms time-per-output-token (TPOT).

cs.DC↗

arXiv2026

Strain Engineering of Intrinsic Anomalous Hall and Nernst Effects in Altermagnetic MnTe at Realistic Doping Levels

Hexagonal MnTe has emerged as a prototypical g-wave altermagnet, hosting time-reversal symmetry breaking in momentum space despite a vanishing net magnetization. While this symmetry breaking theoretically allows for an intrinsic anomalous Hall effect, experimentally observed signals have remained weak. In this work, we investigate the origin of this suppression and demonstrate a strategy to amplify anomalous transport responses within the experimentally accessible doping regime. Using a $\bm{k}\cdot\bm{p}$ effective model, we reveal that near the valence band maximum, which corresponds to the energy window relevant for typical hole doping ($\sim10^{19}cm^{-3}$), the intrinsic Hall effect is suppressed due to a symmetry-enforced cancellation of opposing Berry curvature contributions. We propose that breaking the crystalline symmetry via volume-conserving biaxial strain lifts this cancellation, resulting in a significant enhancement of the anomalous Hall conductivity by orders of magnitude. This strain-induced Fermi surface distortion also amplifies the anomalous Nernst effect. Furthermore, the analysis of the spin texture confirms that these strain-enabled anomalous transport signatures emerge while preserving the zero net magnetization.

cond-mat.mtrl-sci↗

arXiv2025

Learned-Rule-Augmented Large Language Model Evaluators

Large language models (LLMs) are predominantly used as evaluators for natural language generation (NLG) tasks, but their application to broader evaluation scenarios remains limited. In this work, we explore the potential of LLMs as general evaluators across diverse tasks. Although LLM-based evaluators have made progress in different areas, existing methods struggle to generalize due to their reliance on costly, human-designed evaluation principles, which are often misaligned with both annotated data and LLMs' understanding.To address these challenges, we propose a rule-augmented evaluation paradigm. First, we introduce a rule distillation method that automatically extracts scoring rules from data using an LLM-assisted Monte Carlo Tree Search (MCTS), alleviating scalability issues and improving alignment with data. Second, to enable LLMs to effectively apply the learned rules, we propose two strategies: (1) Chain-of-Rule (CoR), which guides LLM to follow distilled rules, and (2) training a rule-augmented LLM evaluator (RuAE) via reinforcement learning, further bridging the gap between rules and LLMs' reasoning. Extensive experiments on diverse tasks demonstrate the effectiveness and generalizability of our approach across various evaluation scenarios.

cs.AI↗

arXiv2025

Probing Axion via Mössbauer Spectroscopy

We propose using the ultra-narrow 88 keV Mössbauer transition in $^{109}$Ag to search for QCD axion dark matter. The sub-eV axion field oscillates coherently, inducing a time-varying effective $\barθ_{\rm QCD}$ angle. This, in turn, modulates the nuclear binding energy. From existing linewidth measurements, we derive constraints on the $f_a^{-1}$-$m_a$ plane that already surpass other laboratory bounds. We further detail an experimental setup to directly probe this time-dependent signature via precision Mössbauer spectroscopy in the gravitational potential. This Letter demonstrates that this approach can significantly extend search capability and probe a vast, unexplored region of axion parameter space. Particularly, this setup can probe axion masses beyond the reach of existing experiments, such as atomic-clock measurements, offering a powerful new way for exploring higher-mass axion dark matter. The sensitivity has the potential to be further improved with advancing experimental capabilities.

hep-ph↗

arXiv2025

Chiral symmetry and peripheral neutron-$α$ scattering

We propose and demonstrate that peripheral neutron-$α$ scattering at low energies can serve as a sensitive and clean probe of the long-range three-nucleon forces. To this aim, we perform {\it ab initio} quantum Monte Carlo calculations using two- and three-nucleon interactions derived in chiral effective field theory up to third expansion order. We show that the longest-range three-nucleon force stemming from the two-pion exchange plays a crucial role in the proper description of the neutron-$α$ $D$-wave phase shifts. Our Letter reveals the predictive power of chiral symmetry in the few-body sector and opens a new direction for probing and constraining three-nucleon forces.

nucl-th↗

arXiv2025

Triaxial relativistic Hartree-Bogoliubov theory in continuum for exotic nuclei

A triaxial relativistic Hartree-Bogoliubov theory in continuum (TRHBc) has been developed to incorporate triaxial deformation, pairing correlations, and continuum effects in a fully microscopic and self-consistent way, aiming for a reliable description of triaxial exotic nuclei with extreme neutron-to-proton ratios. The TRHBc formalism is presented in detail, and its numerical implementation is benchmarked against the results from the axially deformed relativistic Hartree-Bogoliubov theory in continuum and the TRHB theory in harmonic oscillator expansion. The TRHBc theory is applied to investigate the aluminum isotopes systematically, and the available data are well reproduced for the binding energies, one- and two-neutron separation energies, and charge radii. The nuclei near the one-neutron drip line, $^{40}$Al and $^{42}$Al, are found to be triaxially deformed with one-neutron separation energies below 1 MeV. Possible neutron halos in the triaxial nuclei $^{40}$Al and $^{42}$Al are explored by examining the single-particle levels around the Fermi surface, including their composition and contribution to the total neutron density. The existence of neutron halos in $^{40}$Al and $^{42}$Al is also supported by the halo scale, which is comparable to other halo nuclei well-established previously. More importantly, the mechanism for the halo formation in $^{40}$Al is revealed to be the triaxial deformation, which results in the decoupling of the halo orbitals from those of the core.

nucl-th↗