Searcharxiv⌕ Search

arXiv subjects

Dong Sun

Publications and source records attributed to Dong Sun.

At least 19 recordsLinked to original sources
arXiv2026

What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels

Coding agents are increasingly evaluated not only by whether they solve a task, but also by how they execute it. However, existing process-level evaluations often treat action prediction, task uncertainty, and step attribution as if they were the same problem, which makes it unclear what such evaluations actually measure. In this paper, we introduce a measurement framework for process evaluation in coding agents and instantiate step-level causal attribution with SCAE, a replay-based estimator derived from a structural causal model of agent execution. Our framework combines prefix-conditioned identification, replay/intervention-based estimation, and controlled judge-information manipulation to study process evaluation at the action, task, and step levels. Experiments on 499 file-localization episodes from 12 repositories show that next actions are driven primarily by execution provenance rather than code-graph transitions, execution uncertainty is structured at the task rather than step level, and full-trace judges exhibit systematic collider bias, suggesting that current process evaluation often measures semantic relevance rather than certified causal contribution.

cs.AI↗
arXiv2026

Thermochemical non-equilibrium effects on turbulent boundary layers

This investigation employs direct numerical simulations (DNS) of high-Mach-number turbulent boundary layers under three flow conditions: a low-enthalpy calorically perfect gas, and two high-temperature gas mixtures, one in chemical non-equilibrium state and the other in full thermochemical non-equilibrium state. The influences of the two-temperature model on turbulent statistics and the coupling among turbulence, chemistry, and vibrational energy are examined. It is found that while high-enthalpy effects leave the velocity statistics virtually unchanged, they dramatically modify the near-wall temperature field. A pronounced disparity between the translational-rotational temperature and the vibrational temperature arises in the near-wall region, rendering the conventional generalized Reynolds analogy (GRA) inaccurate for vibrational temperature. To remedy this, a novel composite GRA is proposed that blends a vibrational-temperature-based relation with the standard formulation, and it demonstrates excellent agreement with the DNS data. Thermal non-equilibrium effects also substantially alter near-wall chemical reactions: it suppresses O2 dissociation while promoting NO formation, leading to a corresponding decrease and increase in the mean concentrations of O and NO, respectively. Spectral analyses of the turbulence-chemistry and turbulence-vibrational relaxation interaction terms reveal that temperature fluctuations dominate these flow quantities at energy-containing scales. Integrating the resulting spectral functions, we evaluate subgrid-scale closure terms for large-eddy simulation. At small filtering scales, the magnitude of the cross-correlation term rivals or exceeds that of the temperature fluctuation term, whereas the temperature fluctuation term becomes dominant at larger filter scales.

physics.flu-dyn↗
arXiv2026

Temporal-Causal Unity as an Operational Framework for Collective Dynamics: Causal-Progress Clocks, Synchronization, and Polarization

This paper develops temporal-causal unity (TCU), a framework connecting a process-philosophical thesis -- time is the ordered unfolding of causal change -- to an operational model of cognitive and social dynamics. The framework deliberately separates three claims: an interpretive thesis about becoming, a measurable causal-progress coordinate, and a stochastic network model. Causal progress is defined by $\tau(t)=\int_0^t\lambda(s\mid\mathcal H_s)\,{\rm d}s$, where the nonnegative event intensity $\lambda$ must be specified independently of the outcome. Agents carry an orientation phase and an activation amplitude; weighted interaction, heterogeneous drift, external input, anchoring, and diffusion govern their evolution in $\tau$. First- and second-harmonic order parameters separate consensus from bipolar polarization. For the all-to-all noisy Kuramoto special case with Lorentzian drift width $\Delta$, synchronization begins at the conditional threshold $K_c = 2(\Delta + D)$, not at a universal constant. Reproducible numerical illustrations illustrate (not empirically demonstrate) this threshold, causal-clock curve collapse, and the consensus-polarization distinction. Six historical episodes are treated as scope probes rather than validation data. The paper derives falsifiable hypotheses and an out-of-sample protocol for comparing causal-progress and chronological-time models. TCU is therefore offered as a disciplined bridge between process ontology and complex-systems modeling, not as a replacement for spacetime physics or as an empirically established identity between time and causation.

physics.soc-ph↗
arXiv2026

From Fragments to Paths: Task-Level Context Recovery for Large Industrial Codebases

Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remains challenging. Existing methods often retrieve only local fragments and fail to recover the broader task-relevant context needed for complex repository-level tasks. We present DeepDiscovery, a task-level repository-understanding method for large industrial codebases. DeepDiscovery uses a two-stage \textit{Location--Inference} framework to localize high-confidence task anchors and recover broader task-relevant context over multi-relational repository structure under budget constraints. Across controlled method-level evaluation, organization-internal industrial repository-understanding scenarios, and end-to-end evaluation on SWE-bench Verified, DeepDiscovery consistently improves task-relevant file recovery and downstream SE performance. On 27 medium-scale tasks, DeepDiscovery achieves the best file recovery quality among five representative baselines without offline preprocessing. On organization-internal industrial tasks from a production-scale integrated codebase ecosystem, including 27 medium-scale tasks and 40 large-scale tasks, DeepDiscovery improves Full Recall Rate across multiple AI coding systems, with absolute gains ranging from 1.6 to 9.2 percentage points on large subprojects and from 2.5 to 7.4 percentage points on medium-scale subprojects. In a controlled end-to-end evaluation on SWE-bench Verified, a system equipped with DeepDiscovery achieves a 78.6\% Solve Rate, outperforming the corresponding baseline by 8.2 percentage points. These results suggest that stronger task-level repository understanding can improve coding-agent performance on complex SE tasks.

cs.SE↗
arXiv2026

SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction

Joint Entity and Relation Extraction (JERE) is highly sensitive to training data quality, making data augmentation a natural way to improve generalization. However, existing augmentation methods often weaken entity relevance and disrupt semantic structure, limiting their effectiveness for JERE. In this paper, we propose \textbf{Structured Semantic Data Augmentation (SSDAU)}, a method designed to preserve triple-aware semantic structure during augmentation. SSDAU segments text by entity labels, captures semantic features through context-aware encoding, and restructures entity semantics to generate augmented data. To distinguish semantically similar entities, SSDAU combines contextualized embeddings with traditional similarity scores. To reduce topic inconsistency, we apply BERTopic-based filtering to remove irrelevant augmentations. We evaluate SSDAU on datasets with different annotation types and compare its performance on five representative JERE models against seven popular augmentation baselines. Experiments show that SSDAU generates semantically consistent data, is more robust to ambiguity than non-LLM methods (8.95\% vs. 23.58\% average relative F1 decrease), and significantly outperforms strong alternatives in most settings.

cs.CL↗
arXiv2026

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents

Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limited visibility and often miss defects that arise during execution. We present ProcCtrlBench, a benchmark for execution-process evaluation in LLM coding agents. ProcCtrlBench organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories, and evaluates agent trajectories through standardized process evidence rather than final outcomes alone. To support comparison across heterogeneous agents, ProcCtrlBench standardizes raw logs into a unified trajectory representation and reports calibrated scorecards over process-level findings. In addition, ProcCtrlBench uses control preservation as a way to quantify execution-process quality, capturing whether execution remains interpretable, interruptible, correctable, reversible, and able to hand back authority when needed. We evaluate ProcCtrlBench on 200 cases sampled from three benchmarks: AndroidBench, TerminalBench, and SWE-bench-Verified. Results show that ProcCtrlBench can be instantiated with useful reliability, provides more stable semantics than direct thresholding, and reveals meaningful differences in execution quality that are often overlooked by conventional outcome-based evaluation.

cs.SE↗
arXiv2026

Ultrafast Non-Volatile Weyl LuminoMem for Mid-Infrared In-Memory Computing

Integrated optoelectronic systems strive to combine the logic/memory density of electronics with the bandwidth of photonics, but monolithic realization is impeded by the inefficient electronic-to-photonic interface. Current architectures rely on separate readout circuitry and modulators, creating bottlenecks in energy and latency, while existing direct transduction methods often compromise on switching speed or non-volatility. Here, we report an ultrafast, non-volatile optoelectronic memory, named LuminoMem, that integrates electrical storage and mid-infrared light emission in a single device. The device utilizes a floating-gate architecture, in which the Weyl semiconductor tellurium serves simultaneously as a charge-trapping storage layer and an emissive medium. This design enables nanosecond-scale electrical programming of non-volatile photoluminescence at 3.4 um, allowing direct optical access to stored states without external modulation. We demonstrate 4-bit (16-level) optical storage capacity and validate the device's performance through neural network simulations that achieve high accuracy on the Fashion-MNIST dataset. By effectively bridging the gap between electronic storage and mid-infrared photonics, the demonstrated mid-infrared LuminoMem provides a hardware foundation for promoting current computation efficiency and potential intelligent platforms that co-integrate computing, memory, and sensing capabilities.

cond-mat.mtrl-sci↗
arXiv2026

Direct Photocurrent Detection of Optical Vortex Based on the Orbital Photo Galvanic Effect: Progress, Challenge and Perspective

A photodetector that can directly distinguish the orbital angular momentum (OAM) of light is highly desirable for integrated on-chip OAM detection and focal plane array devices. The recent development of OAM detectors based on the intrinsic orbital photo galvanic effects (OPGE) of materials provide a new route for direct OAM detection that is on-chip scalable with high resolution and speed. In this paper, we summarize the current progress in direct photodetection of OAM via OPGE. We begin with a short review of the basic operation scheme of the OAM detector and provide a comprehensive symmetry analysis to sort out the favorable characteristics of the materials, incorporating considerations from device schemes based on various device performance characteristics and specific application circumstances. From that, we review the current experimental progress and technical challenges, then oversee the possible solutions to these challenges and provide a perspective on the future opportunities of this OAM detection route.

cond-mat.mtrl-sci↗
arXiv2026

Gate-Tunable Mid-Infrared Electroluminescence from Te/MoS2 p-n Heterojunctions

Mid-infrared (MIR) emitters are critical components in advanced photonic systems, driving progress in fields such as chemical sensing, environmental monitoring, medical diagnostics, thermal imaging and free-space communications. Conventional MIR emitters based on III-V heterostructures rely on complex epitaxial growth on rigid lattice-matched substrates and suffer from limited integration compatibility with CMOS or flexible platforms. The recent development of novel MIR emitters based on two-dimensional (2D) materials such as black phosphorus (BP) is more suitable for on-chip applications but faces challenges related to stability and emission efficiency. Based on the recently discovered highly efficient photoluminescence of Te, we demonstrate a gate-tunable midinfrared light-emitting diode based on a van der Waals heterojunction formed by multilayer transition metal dichalcogenide (TMD) MoS2 and tellurium (Te). The device emits polarized electroluminescence (EL) centered at 3.5 $\mu$m under forward bias at 25 K, and the EL persists up to 80 K with reduced intensity. Gate control of the MoS2 Fermi level modulates the band alignment and injection efficiency, enabling dynamic tuning of the EL intensity. The emission remains spectrally stable under varying bias and gating, indicating robust band-edge recombination. These results establish the Te/TMD heterostructure as a promising platform for integrated polarized mid-infrared optoelectronics.

cond-mat.mes-hall↗
arXiv2026

ERNIE 5.0 Technical Report

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

cs.CL↗
arXiv2026

Robustness of Mixtures of Experts to Feature Noise

Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling. We study an iso-parameter regime where inputs exhibit latent modular structure but are corrupted by feature noise, a proxy for noisy internal activations. We show that sparse expert activation acts as a noise filter: compared to a dense estimator, MoEs achieve lower generalization error under feature noise, improved robustness to perturbations, and faster convergence speed. Empirical results on synthetic data and real-world language tasks corroborate the theoretical insights, demonstrating consistent robustness and efficiency gains from sparse modular computation.

cs.LG↗
arXiv2025

Versatile tunable optical injection of chiral polarized Weyl fermions in a magnetic Weyl semimetal Co3Sn2S2

Precise probe and control of various quantum degrees of freedom in novel quantum matter are central to understanding fundamental quantum physics and hold promise for innovative routes to encode and process information. Chirality is one such degree of freedom that has recently attracted intense research interest, especially for Weyl fermions in topological Weyl semimetals. The coupling of chiral degrees of freedom through light-matter interactions and the versatile control of these couplings through external fields can lead to precise quantum control of Weyl fermions. In this work, we demonstrate the observation of light chirality-dependent photocurrent in the mid-infrared regime. Excitation wavelength-dependent measurements reveal that the photocurrent originates from the injection of chiral polarized Weyl fermions by chiral polarized mid-infrared photons. The optical process that generates unbalanced chiral polarized Weyl fermions is determined to be a third-order nonlinear photocurrent process. Compared with nonmagnetic Weyl semimetals, such coupling is versatilely tunable in magnetic Weyl semimetals with the magnetization direction and external electric field in addition to the chirality of light. Our results are not only directly applicable to tunable circular-polarization-sensitive photodetection in the mid-infrared regime, but also pave the way toward functional quantum devices that utilize the chiral quantum degrees of freedom of Weyl fermions.

cond-mat.mes-hall↗
arXiv2025

Observation of Berry Curvature-Enhanced Anomalous Photo-Nernst Effect in Magnetic Weyl Semimetal

The anomalous Nernst effect is the thermoelectric counterpart of the anomalous Hall effect, which can emerge in magnetic materials or topological materials without magnetic field. Such effect is critical to both fundamental topological physics and various application fields, including energy harvesting, spintronics and optoelectronics. In this work, we observe the anomalous photo-Nernst effect, which use light excitation to generate temperature gradients for the thermoelectric response. Our experiments reveal a pronounced edge photocurrent response in magnetic Weyl semimetal Co3Sn2S2 under zero magnetic field, originating from the anomalous photo-Nernst effect. The pronounced photo-Nernst current benefits from the exceptional properties of Co3Sn2S2, including the large thermoelectric coefficient, topologically enhanced anomalous response of Weyl bands and the Shockley-Ramo nature of long-range photocurrent generation. Furthermore, by comparing the nominal anomalous Nernst coefficient under different wavelength excitations, we observe a clear enhancement in the mid-infrared region, originating from the topological contribution from the large Berry curvature of Weyl bands. Our results reveal the interplay among light, magnetism, and topological order in magnetic Weyl semimetals, which not only offers insights for fundamental physics but also advances potential applications in quantum devices.

cond-mat.mtrl-sci↗
arXiv2025

High-speed readout for direct light orbital angular momentum photodetector via photoelastic modulation

Recent progress in direct photodetection of light orbital angular momentum (OAM) based on the orbital photogalvanic effect (OPGE) provides an effective way for on-chip direct electric readout of orbital angular momentum, as well as large-scale integration focal-plane array devices. However, the recognition of OAM order from photocurrent response requires the extraction of circular polarization-dependent response. To date, the operation speed of such detector is currently at the minute level and is limited by slow mechanical polarization modulation and low OAM recognition capability. In this work, we demonstrate that the operation speed can be greatly improved via electrical polarization modulation strategy with photoelasitc modulator accompanied by phase-locked readout approach with lock-in amplifier. We demonstrate an operation speed of up to 1 kHz with this new technology in the mid-infrared region (4 {\mu}m) on an OAM detector using multilayer graphene (MLG) as photosensitive material. In principle, with new modulation and readout scheme, we can potentially increase the operation speed to 50.14 kHz with a PEM that operates at a state-of-the-art speed. Our work paves the way toward high-speed operation of direct OAM detection devices based on OPGE effect and pushes such technology to a more practical stage for focal plane array applications.

physics.optics↗
arXiv2024

High Discrimination Ratio, Broadband Circularly Polarized Light Photodetector Using Dielectric Achiral Nanostructures

The on-chip measurement of polarization states plays an increasingly crucial role in modern sensing and imaging applications. While high-performance monolithic linearly polarized photodetectors have been extensively studied, integrated circularly polarized light (CPL) photodetectors are still hindered by inadequate discrimination capability. In this study, we employ achiral all-dielectric nanostructures to develop a broadband CPL photodetector with an impressive discrimination ratio of ~107 at the wavelength of 405 nm, significantly surpassing its counterparts by two orders of magnitude. Our device shows outstanding CPL discrimination capability across the visible band without requiring intensity calibration. Its function mechanism is based on the CPL-dependent near-field modes within achiral structures: under left or right CPL illumination, distinct near-field modes are excited, resulting in asymmetric irradiation of the two electrodes and generating a photovoltage with directions determined by the chirality of the incident light field. The proposed design strategy facilitates the realization of ultra-compact CPL detection across diverse materials, structures, and spectral ranges, presenting a novel avenue for achieving high-performance monolithic CPL detection.

physics.optics↗
arXiv2024

Contextual Embedding Learning to Enhance 2D Networks for Volumetric Image Segmentation

The segmentation of organs in volumetric medical images plays an important role in computer-aided diagnosis and treatment/surgery planning. Conventional 2D convolutional neural networks (CNNs) can hardly exploit the spatial correlation of volumetric data. Current 3D CNNs have the advantage to extract more powerful volumetric representations but they usually suffer from occupying excessive memory and computation nevertheless. In this study we aim to enhance the 2D networks with contextual information for better volumetric image segmentation. Accordingly, we propose a contextual embedding learning approach to facilitate 2D CNNs capturing spatial information properly. Our approach leverages the learned embedding and the slice-wisely neighboring matching as a soft cue to guide the network. In such a way, the contextual information can be transferred slice-by-slice thus boosting the volumetric representation of the network. Experiments on challenging prostate MRI dataset (PROMISE12) and abdominal CT dataset (CHAOS) show that our contextual embedding learning can effectively leverage the inter-slice context and improve segmentation performance. The proposed approach is a plug-and-play, and memory-efficient solution to enhance the 2D networks for volumetric segmentation. Our code is publicly available at https://github.com/JuliusWang-7/CE_Block.

eess.IV↗
arXiv2023

STOPNet: Multiview-based 6-DoF Suction Detection for Transparent Objects on Production Lines

In this work, we present STOPNet, a framework for 6-DoF object suction detection on production lines, with a focus on but not limited to transparent objects, which is an important and challenging problem in robotic systems and modern industry. Current methods requiring depth input fail on transparent objects due to depth cameras' deficiency in sensing their geometry, while we proposed a novel framework to reconstruct the scene on the production line depending only on RGB input, based on multiview stereo. Compared to existing works, our method not only reconstructs the whole 3D scene in order to obtain high-quality 6-DoF suction poses in real time but also generalizes to novel environments, novel arrangements and novel objects, including challenging transparent objects, both in simulation and the real world. Extensive experiments in simulation and the real world show that our method significantly surpasses the baselines and has better generalizability, which caters to practical industrial needs.

cs.RO↗
arXiv2023

On the characteristic length scale for the synthetic turbulence based on the Spalart-Allmaras model

In the hybrid RANS-LES simulations, proper turbulent fluctuations should be added at the RANS-to-LES interface to drive the numerical solution restoring to a physically resolved turbulence as rapidly as possible. Such turbulence generation methods mostly need to know the distribution of the characteristic length scale of the background RANS model, which is important for the recovery process. The approximation of the length scale for the Spalart-Allmaras (S-A) model is not a trivial issue since the model's one-equation nature. As a direct analogy, the approximations could be obtained from the definition of the Prandtl's mixing length. Moreover, this paper proposes a new algebraic expression to approximate the intrinsic length scale of the S-A model. The underlying transportation mechanism of S-A model are largely exploited in the derivation of this new expression. The new proposed expression is employed in the generation of synthetic turbulence to perform the hybrid RANS-LES simulation of canonical wall-bounded turbulent flows. The comparisons demonstrated the feasibility and improved performance of the new length scale on generating synthetic turbulence at the LES inlet.

physics.flu-dyn↗