arXiv subjects

Hao Li

Publications and source records attributed to Hao Li.

At least 19 recordsLinked to original sources

arXiv2026

Thermally enhanced magnon-phonon resonance in van der Waals antiferromagnet FePS3

Strong coupling between collective excitations provides a route to controlling quantum states of matter, yet its evolution under thermal fluctuations remains poorly understood. In the van der Waals antiferromagnet FePS3, strong magnon-phonon coupling is established at low temperatures. At the same time, recent terahertz experiments revealed the counterintuitive stabilization of a long-lived metastable magnetic state with an exceedingly long lifetime of 5 msec at the antiferromagnetic transition, not at the base temperature. This was attributed to a strongly coupled spin-lattice scenario, challenging the conventional wisdom that increased magnetic and thermal fluctuations near TN should be detrimental to the coherent control of a metastable phase. Thus it requires an independent examination for correct understanding. Using high-field Raman spectroscopy, we systematically investigate the temperature evolution of magnon-phonon coupling in FePS3. We observe a pronounced avoided crossing between magnon and phonon modes across a wide range of temperatures and find that the coupling strength remains remarkably robust with increasing temperatures. The zero-field magnon-phonon detuning decreases progressively with warming, driving the system toward resonance and thereby enhancing their hybridization near the transition temperature. This anomalous thermal evolution provides the crucial key to understanding the unusual terahertz-driven states recently reported in FePS3. More broadly, our results highlight van der Waals magnets as a promising platform for strong coupling among collective excitations and for controlling magnetic states through light-matter interactions.

cond-mat.mtrl-sci↗

arXiv2026

Agentic Software Engineering: Foundational Pillars and a Research Roadmap

Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.

cs.SE↗

arXiv2026

SynBench: A Benchmark for Differentially Private Text Generation

Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regulatory boundaries, while bounding the risks of re-identification and membership inference. LLM-based methods deliver promising results; however, comparisons are exacerbated by differing evaluation setups and "private" datasets, potential pre-training contamination is not considered and guarantees are not verified with DP audits. To advance this field, we introduce a unified evaluation framework with standardised utility and fidelity metrics and privacy audits, encompassing nine curated datasets that capture domain-specific complexities such as technical jargon, long-context dependencies, and specialised document structures. In a large-scale empirical study, we benchmark LLM-based state-of-the-art DP text generators of varying sizes (between 1--8B). Our results indicate that DP synthetic text generation remains an unsolved challenge, with quality deteriorating more as the private datasets deviate further from the generators' pre-training corpora. Our analyses suggest that synthetic data quality may be overestimated when LLMs have been pre-trained---without DP---on portions of the "private" data to be generated, and our membership inference (MIA) auditing setup for synthetic text reveals measurable membership signals even under tight privacy budgets. Finally, we note that under the "public pre-training, private generation" paradigm, the nominal $(\varepsilon,δ)$ guarantee does not account for exposure during pre-training, motivating contamination-aware evaluation of DP synthetic text generation. Code and data splits: https://github.com/ImperialGlobalSingapore/synbench

cs.AI↗

arXiv2026

New Wine in an Old Bottle -- NeuralPOM: A Hybrid Ocean Forecast Model with Differentiable Dynamics and Staged Learning

Coarse-grid ocean circulation models rely on empirical subgrid parameterizations that struggle to capture mesoscale eddies, whereas purely data-driven neural forecasters accumulate trajectory drift, violate tracer conservation, and damp small-scale variability over extended integrations. Here we present NeuralPOM, a hybrid ocean forecast model that couples differentiable explicit mode-split and semi-implicit free-surface implementations of the Princeton Ocean Model (POM) to a conservation-constrained neural corrector. The three-dimensional primitive-equation solver advances the ocean state, while the neural network periodically updates the physical fields at high-frequency (1 h) or low-frequency (1 day) intervals under volume, heat, and salt conservation constraints. Using a fine-grid reference dataset exceeding 100,000 model days in a wind-driven double-gyre basin, we introduce a three-stage training procedure comprising offline single-step pretraining, multi-step differentiable training through the ocean solver, and multi-day closed-loop rollout training. Over 100-day forecasts, NeuralPOM reduces errors across all prognostic fields relative to coarse-grid physical closures and direct neural forecasters, preserving mesoscale kinetic energy while improving eddy phase alignment. Controlled ablations show that closed-loop training suppresses multi-day drift, whereas backpropagating gradients through the differentiable solver stabilizes high-frequency coupling. Finally, because high-frequency tracer updates can introduce density anomalies via the equation of state that excite spurious baroclinic pressure gradients, we introduce Density-Normal Damping (DND) to attenuate the density-modifying (diapycnal) tracer component while retaining the density-compensated (isopycnal) correction.

physics.ao-ph↗

arXiv2026

Xiaomi Auto World Model 2.0: Causal World Models for Real-World Driving and Embodied Intelligence

We present Xiaomi Auto World Model 2.0, a unified streaming causal world model for Physical AI. It models and generates causal physical evolution in the real world, and unifies heterogeneous conditioning inputs for view-consistent generation. The architecture integrates View-Temporal Attention (VTA) to capture cross-view spatial dependencies and temporal dynamics, together with Multi-view Rotary Position Encoding (RoPE) to encode positional relationships across views and time. WorldRec 2.0 reconstructs static and dynamic 3D Gaussians from multi-view, multi-temporal observations in a single forward pass and uses their renderings as explicit scene context to preserve geometry and appearance during long-horizon generation. Conditioning inputs are fused through VAE latent concatenation in a shared representation space. We incorporate Gated Linear Attention (GLA) into the temporal layers of VTA for efficient streaming inference, reducing computation and KV-cache memory during multi-view rollouts. A physical-interaction data pipeline covers diverse interactions and long-tailed events. From Pre-train onward, these data are combined with large-scale videos and heterogeneous visual modalities to learn visual, geometric, and dynamic priors. During Mid-train, training across diverse view configurations further improves the model's ability to capture how actions and object states shape subsequent scene evolution. After distillation-based Post-train, we apply the model to closed-loop simulation, closed-loop training, and World Action Model (WAM) applications. These applications generate physically consistent future states and support world-state prediction, policy learning, and action generation for Physical AI.

cs.AI↗

arXiv2026

Quantum Noise Spectroscopy of Nanoscale Charge Defects in Silicon Carbide at Room Temperature

The nanoscale charge environment critically influences the performance of semiconductor devices, yet traditional characterization techniques usually lack the spatial resolution to resolve nanoscale charge heterogeneity and identify microscopic noise sources. Here, we address this critical gap by utilizing individual PL5 color centers in commercial silicon carbide as room-temperature, broadband (near-DC to GHz) quantum spectrometers. We report the first real-time, nanoscale observation of single-charge tunneling dynamics at room temperature in 4H-SiC by monitoring the random telegraph noise using optically detected magnetic resonance (ODMR). This capability enables an electrical noise imaging technique that shows distinct noise variations on different wafers. Employing dynamical decoupling and $T_1$ relaxation spectroscopy, we observe correlations of noise spectral density across frequency bands and obtain the nanoscale electron paramagnetic resonance (EPR) fingerprint of spin defects in SiC. Ultimately, through surface chemical engineering, we identify the native oxide layer as the main source of resolved electromagnetic fluctuations. This work establishes a versatile atomic-scale metrology platform bridging quantum sensing and semiconductor engineering, offering critical insights for optimizing third-generation semiconductor interfaces and advancing solid-state quantum technologies.

quant-ph↗

arXiv2026

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models

Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models (WAMs) through two complementary capabilities: video generalization, which predicts the visual evolution of new tasks, and action generalization, which translates these predictions into executable behavior through a video-to-action bridge. By varying video and action supervision for tasks outside an initial training set, we examine their respective contributions to task transfer. On RoboTwin 2.0, using only in-distribution video-action supervision yields a 25.07% success rate on out-of-distribution tasks. Introducing videos of these tasks without their action labels raises success to 55.90%, while adding just one action-labeled demonstration per task further improves it to 70.70%. These findings suggest that broader video coverage enables task transfer by leveraging existing inverse-dynamics capabilities, while even sparse action supervision further strengthens those capabilities. Guided by this perspective, we introduce WorldBridge, a WAM with separate video and action experts connected through structured attention and trained with joint flow matching. WorldBridge incorporates visual memory at two temporal scales and action forcing, alongside a unified data processing pipeline that standardizes and filters heterogeneous robot trajectories and egocentric hand-derived supervision. Across multiple manipulation benchmarks, WorldBridge achieves state-of-the-art performance among the compared methods, including 96.23% on RoboTwin 2.0 full data setting and 80.9% on clean to random setting, 82.8% on RoboCasa GR1 TableTop, and 57.6% on DOMINO Level-1. Our study highlights the complementary roles of video prediction and action grounding in developing robots that generalize across tasks.

cs.RO↗

arXiv2026

A neural network method for scalar conservation laws with convergence rates for shock waves

We propose a new entropy-compatible neural network method for scalar hyperbolic conservation laws and establish, to our knowledge, the first explicit $L^1$ convergence rates in this setting for piecewise smooth entropy solutions, including those with discontinuities. The method is based on a computable approximation of the Kružkov entropy residual that sits between the strong and weak forms of the entropy inequality. For a single regular shock in one dimension and finitely many smooth shock hypersurfaces with transversal interactions in several dimensions, we construct explicit neural networks with provably small loss by combining shock-adapted continuous piecewise linear functions with known approximation properties of $\tanh$ neural networks. The one-dimensional analysis also covers rarefactions, compound waves, regular shock interactions, and nondegenerate shock formation from smooth initial data. Together with entropy-based stability estimates, this gives rigorous $L^1$ error bounds for minimizers of the proposed loss. In particular, when the network size grows in proportion to the number of degrees of freedom of a space--time mesh of size $h$, the analysis recovers the classical Kuznetsov rate $O(h^{1/2})$ in shock-dominated cases. Numerical experiments in one and two space dimensions illustrate the performance of the method.

math.NA↗

arXiv2026

CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.

cs.AI↗

arXiv2026

AnchorKV: Lossless Key-Value Cache Reconstruction from Layer-Sparse Residual Anchors

Residual-stream caching can reconstruct transformer key-value (KV) caches losslessly, but its memory advantage depends on architecture. We present AnchorKV, a storage-replay spectrum connecting per-layer residual caching and full recomputation through configurable residual anchors. An architecture-dependent break-even rule identifies the first storage-saving spacing, while deployment selects an operating point from the spectrum and cascade replay reduces reconstruction from O(Ls) to O(L), with L the model depth and s the anchor spacing. For interleaved sliding-window architectures, exact dynamic programming places anchors under non-uniform reconstruction demand. Across CPU, CUDA, and Ascend NPU backends, six architecture families, and fp32/bf16 arithmetic, evaluations verify bit-exact KV reconstruction and unchanged continuation logits and tokens. At 4k context, cascade reconstruction is up to 16.3 times faster than naive replay; across eight applicable global-attention checkpoints at 32k context, deepest spacing yields 5.78-54.0 times full-KV reactivatable session capacity. Compared with seven external cache methods on a common model, AnchorKV preserves full-cache retrieval and question-answering scores, whereas lossy methods change output fidelity and task scores. The break-even spacing is computable from a model's configuration file alone.

cs.AR↗

arXiv2026

Exploiting Pinching Antenna Systems in NOMA Covert Communication Networks

Pinching antenna systems (PASS) provide flexible transmitter-side radiation reconfiguration for high-frequency wireless communications. This paper applies PASS to non-orthogonal multiple access (NOMA) covert communication networks, where activated pinching antennas (PAs) transmit superimposed signals to a pair of users stochastically distributed within a rectangle. Two passive wardens respectively monitor the downlink transmissions intended for two users. More specifically, we derive the closed-form detection error probability (DEP) expressions for two wardens under bounded noise uncertainty. Then we analytically determine the optimal detection thresholds and minimum DEPs in the worst-case covert detection scenarios. The covert transmission rates of two users are further characterized by taking into consideration ideal successive interference cancellation and non-ideal successive interference cancellation at near user and intra-NOMA interference at far user. Numerical results are presented to confirm that: 1) PASS-NOMA is capable of providing higher covert rates relative to conventional orthogonal multiple access OMA schemes; 2) As the number of activated PAs begun to increase, the near user has ability to obtain a larger covert rate gain than far user; and 3) The DEP of PASS-NOMA networks is larger than that of both PASS-OMA and traditional antenna based NOMA in specific output power regions.

cs.IT↗

arXiv2026

Magnetic Imaging with High Spatial Resolution Using a Single Niobium-Nitride-Based Three-Dimensional Nanobridge Junction

The nanobridge junctions (NBJs) allow the miniaturization of the Superconducting Quantum Interference Device (SQUID) and improve the spatial resolution of scanning SQUID microscopy. However, the SQUID loop diameter imposed a fundamental limit on the resolution. In this work, we proposed a single niobium-nitride-based three-dimensional nanobridge junction (NbN-3D-NBJ) alternative to the nanoSQUID for high-resolution magnetic imaging. The critical current of an NbN-3D-NBJ showed an nearly monotonic dependence on the external magnetic field, enabling nanoscale mapping of the magnetic field distribution by measuring the junction's critical current with an intrinsic noise level of 100 nT/Hz^1/2. Using a NbN-3D-NBJ probe, we successfully imaged an Abrikosov vortex in a niobium film with a minimal full width at half maxima (FWHM) of 530 nm, constrained by the distance from the junction to the probe tip edge. Furthermore, we resolved 80 nm spacings between the superconducting nanowires utilizing a second probe with an optimized junction-to-tip distance. Thus, the single 3D NbN NBJ probe has been demonstrated as an effective approach for magnetic imaging with ultra-high spatial resolution.

cond-mat.mes-hall↗

arXiv2026

Efficient Image Synthesis with Sphere Latent Encoder

Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines.

cs.CV↗

arXiv2026

Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks

As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanied by comprehensive system cards, open-weight models receive less scrutiny regarding frontier risks. To address this gap, we present an independent safety evaluation of DeepSeek V4.1 Flash-1017, the latest version of V4.1 Flash that departs from V4 with a new architecture, scaled-up training, and strong agentic capabilities. Drawing on the EU General-Purpose AI Code of Practice, we evaluate the model across 34 benchmarks, including 5 in-house suites, spanning evaluation integrity, loss of control, and harmful manipulation. Conforming to the AEF-1 standard, we compare V4.1 Flash-1017 against V4.1 Flash, earlier DeepSeek V4 models, and leading closed-source systems (GPT-6 Astra, GPT-5.6 Sol, and Gemini 3.8 Flash). Overall, V4.1 Flash-1017 shows substantial safety improvements over the V4 generation and approaches or matches leading closed-source baselines on several dimensions, while still exhibiting notable behaviors that warrant continued attention. Building on our findings, we highlight three key observations and recommendations. First, because safety can shift and even regress across minor updates, developers should integrate safety evaluation into incremental releases. Second, as final-turn outputs and end-state checks alone cannot reliably detect loss-of-control behaviors, deployments require process-level observability across both reasoning traces and action logs. Third, because public benchmarks elicit strong evaluation awareness and face data contamination risks, developing private benchmarks is essential for trustworthy frontier evaluation.

cs.CL↗

arXiv2026

Agent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures

AI coding agents such as Claude Code, GitHub Copilot coding agent, and Cursor now commit directly to open-source repositories. Empirical studies of these agents identify their commits through authorship signatures, such as bot accounts and Co-authored-by trailers. These signatures are optional, can be removed, and are often attached to pull requests rather than to individual commits. Hence, it is unclear whether Agent commits can be told apart from Human commits once the signatures are gone. We investigate the signals and limits of signature-free detection using 7,837,946 commits from 1,226 repositories, covering five coding agents and Human commits. After signatures are masked, detectors rank Agent commits above Human commits with a ROC AUC of up to 0.859, and most of this signal comes from message verbosity and change size rather than from the code itself. On the shared sample, gpt-6-sol without fine-tuning reaches AUCs similar to XGBoost and TF-IDF. At the observed Agent share, however, the best detector on the full test set reaches a precision of only 0.332. Detection transfers poorly to held-out Claude Code and Copilot, with TF-IDF reaching an AUC of only 0.524 for Claude Code. Temporal changes also depend on the agent, e.g., Copilot AUC drops and later recovers, while more training history helps Claude Code but not Copilot. These results indicate that signature-free detection can prioritize commits for review but cannot replace recorded attribution, and that studies relying on signature-based labels should treat them as a lower bound on agent activity.

cs.SE↗

arXiv2026

Agentic Refactoring: An Empirical Study of AI Coding Agents

Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are changing how software is developed. These AI-powered systems function as autonomous teammates capable of planning and executing complex development tasks. Agents have become active participants in refactoring, a key practice for improving internal code quality without altering observable behavior. Despite their increasing adoption, there is little empirical understanding of how agentic refactoring is used in practice, how it compares to human-driven refactoring, and what impact it has on code quality. To address this gap, we present a large-scale study of AI agent-generated refactorings in real-world open-source Java projects, analyzing 51,412 refactoring instances across 12,256 pull requests and 14,998 commits based on the AIDev dataset. We find that refactoring is a common and intentional activity, with agents explicitly targeting refactoring in 26.1% of commits. The subsequent analyses of refactoring types, purposes, and code quality focus on the 3,907 commits (32,611 instances) with explicit refactoring intent. High-level refactorings form the largest category overall; however, agentic refactoring contains a slightly larger share of low-level, consistency-oriented edits than human refactoring (27.6% vs. 24.4%), and its two most frequent operations are Rename Variable (7.6%) and Change Variable Type (6.8%). Additionally, the stated motivations behind agentic refactoring focus overwhelmingly on internal quality concerns (52.5% maintainability and 28.1% readability), although the measured metric improvements from these frequent low-level refactorings remain limited. Finally, code quality metrics show that agentic refactoring yields small but statistically significant improvements in structural metrics, particularly for medium-level changes, reducing class size and complexity.

cs.SE↗

arXiv2026

Halo formation and distribution around cosmic web

We use the ELUCID simulation to study how the local environment affects the formation of dark matter halos and their spatial distribution around the cosmic web. We describe the environment by local density and cosmic-web type. At fixed web type, the halo mass function (HMF) depends strongly on the local density, whereas at fixed density it depends only weakly, though significantly, on the web type; the character of both dependencies changes around the mean density. The halo formation redshift is primarily driven by local density rather than cosmic web. We then introduce the three-dimensional cosmic-web cross-correlation function (3D-WCCF), which expresses the distribution of halos around cosmic web in the local tidal eigenframe. The 3D-WCCF provides numerous anisotropic characteristics. Around all web types, halos are most strongly correlated along the axis of weakest compression, $\mathbf{e}_3$, and least along the axis of strongest compression, $\mathbf{e}_1$. Nearly all cluster-sized halos reside in knots and lie preferentially in the plane perpendicular to ${\bf e}_1$. The 3D-WCCF also provides important information on the geometry and size of filaments, sheets and voids. Moreover, early-forming halos are more strongly correlated with the web than late-forming ones, and this assembly bias is anisotropic around filaments, sheets, and voids, being strongest along $\mathbf{e}_3$, but nearly isotropic around knots.

astro-ph.CO↗

arXiv2026

Intrinsic Raman Modes and Crystal Symmetry of Altermagnetic $α$-MnTe

Crystal symmetry governs the physical properties of materials and provides the framework for interpreting their microscopic excitations and macroscopic responses. In altermagnets, the crystal symmetries that relate opposite-spin sublattices give rise to momentum-dependent spin splitting despite compensated magnetization. Determining the real crystal symmetry is therefore essential for understanding the intrinsic electronic and magnetic properties. For the altermagnetic semiconductor $α$-MnTe, conflicting Raman assignments have left both its intrinsic lattice excitations and its crystal symmetry unresolved. Here we combine high-resolution Raman and second-harmonic generation (SHG) spectroscopy with first-principles calculations to distinguish intrinsic lattice excitations from Te-derived spectral contributions and to examine bulk inversion symmetry of $α$-MnTe. We show that several prominent Raman features previously assigned to $α$-MnTe instead originate from segregated Te clusters or precipitates. The remaining intrinsic Raman response consists of a single Raman-active mode assigned to the calculated $E_{2g}$ phonon, consistent with the centrosymmetric $D_{6h}$ symmetry. The SHG response agrees with surface electric-dipole and bulk electric-quadrupole contributions expected for a centrosymmetric $D_{6h}$ crystal, supporting the preservation of bulk inversion symmetry in $α$-MnTe. Our findings revise the Raman assignments in $α$-MnTe and provide a basis for interpreting its altermagnetic properties within the appropriate crystal-symmetry framework.

cond-mat.mtrl-sci↗