arXiv subjects

Hongrui Zhang

Publications and source records attributed to Hongrui Zhang.

At least 19 recordsLinked to original sources

arXiv2026

High-Temperature ferromagnetism from site-selective filling in (Fe,Ni)$_{6-\delta}$GeTe$_2$

The discovery of high-temperature ferromagnetism in the metallic van der Waals (vdW) system Fe$_N$GeTe$_2$ has brought two-dimensional (2D) magnets into technologically relevant temperature scales. Specifically at N = 5, dilution of magnetic moments by nickel substitution counterintuitively achieves a record high Curie temperature of 478~K. Unraveling the origin of this nickel-substitution-induced enhancement is complicated by the compound's structural complexity, coexistent itinerant and local magnetic contributions, and mesoscopic compositional domains. Through coordinated structural and electronic characterization, we identify that the high-T$_C$ magnetic phase arises from a strain-stabilized Fe$_6$GeTe$_2$ nano-precipitate. Combining first-principles calculations and spin- and angle-resolved photoemission spectroscopy (ARPES), we uncover a site-specific electronic landscape in which interior iron atoms primarily host localized moments while the outer iron atoms neighboring the tellurium layers produce spin-polarized itinerant carriers that cross the vdW gap. The large energy cost associated with homogeneous nickel substitution is found to favor the spontaneous precipitation of the crystallographically and electronically ``clean'' high-T$_C$ phase. Finally, we compare metal-rich vdW magnets with binary magnetic alloys, and discuss the unifying roles of nano-precipitates in stabilizing otherwise unattainable bulk phases. Our work provides mechanistic insights into the record-high T$_C$ ferromagnetism in (Fe,Ni)$_{5+\delta}$GeTe$_2$, establishing a rigorous foundation for the atomic engineering of vdW magnetic metals informed by direct electronic signatures.

cond-mat.mtrl-sci↗

arXiv2026

Eight-unit-cell electronic modulations in cuprates originating from local molecular orbitals

The pair density wave (PDW) state with eight-unit-cell (8a0) periodicity has been widely regarded as the primary order in cuprates, yet its existence and origin remain subjects of intense debate. Using spectroscopic imaging scanning tunneling microscopy, we observe spatial modulations of the electronic states with approximately 8a0 periodicity in both the superconducting and insulating regimes of hole-doped Ca2CuO2Cl2 cuprate. We find that the 8a0 spatial patterns are generated by the formation of molecular orbitals by doped holes, which organize into 4a0*4a0 plaquettes as the basic unit. Our results identify the 4a0 molecular orbital as the fundamental electronic building block in cuprates, while the 8a0 PDW represents a spatial subharmonic that emerges at sufficiently high doping.

cond-mat.supr-con↗

arXiv2026

Q-Edge: Symmetry-Reduced Quantum Simulation of Structured Extreme Dependence

High-dimensional simulation of multivariate extremes is fundamentally limited by the combinatorial complexity of dependence, often more than by the scarcity of extreme observations. We show that symmetry admits a lossless orbit-space representation that preserves structured extreme dependence while replacing an exponentially large dependence space with a compact set of symmetry classes. Based on this principle, we develop Q-Edge (Quantum Extreme Dependence Engine), a symmetry-reduced quantum framework that operates directly in orbit space, enabling scalable simulation and digital twins of structured extreme systems. By transferring symmetry into the data representation rather than the quantum circuit, Q-Edge allows unconstrained quantum generative models to exploit dramatically reduced state spaces. For a 30-dimensional problem, approximately 1.6 million angular states collapse to 256 orbit states, reducing the required quantum representation from about 21 qubits to 8. Our results establish a general computational principle for scalable quantum simulation of structured extreme dependence.

quant-ph↗

arXiv2026

ASI-Bench: At the Dawn of Artificial Superintelligence

Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and turning new ideas into verifiable results. However, the capabilities of today's AI systems are still largely built on learning, compressing, and applying existing human knowledge. Accordingly, existing benchmarks primarily test whether AI can produce correct answers based on learned knowledge, or whether it can complete tasks under extensive human guidance. We therefore introduce ASI-Bench, the first benchmark to jointly evaluate AI systems' capabilities of innovative exploration and autonomous scientific execution across general research domains, and the first to progressively withdraw human methodological guidance within the same research project to test how far AI can proceed on its own. Built by over 40 experts with the cost of 31,000+ human hours, ASI-Bench contains 60 project-level research tasks across 11 scientific domains and progressively reduces methodological guidance to test whether AI can independently select methods, conduct research, and produce verifiable results. All tasks undergo expert review, AI-assisted auditing, sandbox execution, and scorer validation. Across 18 state-of-the-art agent--model configurations, the average score drops from 50.91 with full methodological guidance to 29.10 with only the method specified and 26.62 when agents must determine the method themselves. This sharp decline shows that current systems remain heavily dependent on human guidance and are still far from autonomously conducting end-to-end, project-level scientific research. ASI-Bench is open to the world. We invite researchers and builders everywhere to contribute new tasks, challenge the limits of today's AI, and help accelerate humanity's collective path toward artificial superintelligence at https://asibench.apexin.ai/submit.

cs.AI↗

arXiv2026

RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills

Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress is often limited by the scarcity and narrow diversity of real-world data. The RoboSynChallenge competition introduces a unified benchmark to evaluate and advance the generalizability of manipulation policies across a spectrum of tasks, environments, and difficulty levels. To alleviate the shortage of realistic data, the challenge integrates large-scale synthetic data generation with standardized real-world robotic evaluation. Participants are encouraged to leverage synthesized state-action trials to improve general-purpose policy learning, while final assessments are conducted exclusively on unseen real-world manipulation environments. Baseline implementations, including Transformer-, Diffusion-, Vision-Language-Action, and World-Action-Model-based policies, are provided to ensure reproducibility and comparability. By coupling scalable simulation-based training with rigorous real-world validation, RoboSynChallenge aims to foster the development of broadly capable, data-efficient, and adaptable manipulation systems, thereby paving the way toward truly general robotic intelligence.

cs.RO↗

arXiv2026

MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement

Affective Image Content Analysis (AICA) aims to recognize and understand emotions elicited by visual content, representing an indispensable step toward Artificial General Intelligence (AGI). However, despite the rapid progress of Multimodal Large Language Models (MLLMs), systematic evaluation of their visual emotional intelligence remains largely absent from recent model releases. We attribute this gap to a structural mismatch between conventional AICA paradigms and the open-ended, instruction-driven nature of MLLMs, where further analysis reveals four major limitations: omission of plausible responses, limited emotion taxonomies, neglect of contextual factors, and labor-intensive annotation. To overcome these barriers, we introduce Emotion Statement Judgement (ESJ), a statement-verification formulation that preserves the expressiveness of the input space while constraining outputs to discriminative judgements. We further develop INSETS, a labor-efficient pipeline that instantiates ESJ at scale by constructing INSETS-462k and supporting MVEI, a rigorously refined benchmark spanning sentiment polarity, emotion interpretation, scene context, and perception subjectivity. Beyond evaluation, we build EmObserver, an emotion-oriented MLLM optimized on ESJ through an elaborate multi-stage recipe. Extensive evaluation of broad-spectrum MLLMs on MVEI reveals fine-grained insights into current artificial visual emotional intelligence, while experiments on multiple AICA benchmarks demonstrate the accuracy, generalization, and reasoning faithfulness of EmObserver. Collectively, these results establish ESJ as a practical formulation, MVEI as a comprehensive benchmark, and EmObserver as an advanced baseline for advancing MLLM-oriented visual emotional intelligence. Code will be released at: https://github.com/wdqqdw/EmObserver.

cs.CV↗

arXiv2026

Agentic System as Compressor: Quantifying System Intelligence in Bits

Large language models are turning from isolated predictors into agentic systems: they call tools, retrieve evidence, obey environment constraints, use verifiers, and complete tasks through search and multi-turn interaction. We adopts an analytical viewpoint based on "compression is intelligence": under a fixed task distribution, interface, and compute budget, a stronger agentic system lets a target object be reconstructed with fewer bits. We operationalize the measure with arithmetic coding, seed coding, and a fallback, and evaluate it in five settings: reversed text, chess moves, protein sequences, retrieval-augmented question answering, and semantic story compression; in all of them agentic components reduce codelength. These small, controlled experiments cover component types typical of real agentic systems, show that codelength can analyze how components, observers, and budgets change residual uncertainty, and offer guidance for evaluating real agent systems.

cs.AI↗

arXiv2026

Multimodal Emotion Recognition with Large Language Models

Multimodal Emotion Recognition (MER) focuses on identifying and interpreting emotions from modality-compound inputs. Closely mirroring human cognitive processes in real-world environments, MER has drawn substantial attention from both academia and industry. Recently, a paradigm shift has been unveiled in MER, from leveraging small-scale, task-specific models to Large Language Models (LLMs). We refer to the latter as the MER-with-LLMs paradigm, which offers unprecedented generality, spurring numerous empirical attempts, even alongside speculation about LLMs' potential to achieve general emotional intelligence. However, with these new opportunities come new challenges, including the scarcity of emotionally annotated data, the affective gap both within and across modalities, and the opacity of affective interpretation. To systematically review existing research and guide future exploration, this paper categorizes prior works according to their focus on addressing these challenges into three directions: Affective Data Augmentation, Multimodal Affective Representation, and Multimodal Affective Reasoning. By thoroughly tracing the development, emerging trends, and remaining issues within each direction, this paper aims to provide a clear academic map of the MER-with-LLMs paradigm and foster its structured advancement.

cs.MM↗

arXiv2026

Mapping Metastable Magnetic Textures in (Fe0.5Co0.5)5GeTe2 with in-situ Lorentz Transmission Electron Microscopy

Topologically protected magnetic textures are a promising route to low-energy control of magnetism, but they are most often studied away from ambient conditions, typically at low temperatures and high magnetic fields. Here we use in-situ Lorentz transmission electron microscopy with control of temperature and magnetic field to investigate the skyrmion metastability in (Fe0.5Co0.5)5GeTe2 (FCGT). By field-cooling FCGT in magnetic fields of different magnitude to different base temperatures and then removing the applied field, we create meta(stable) zero-field magnetic states. We use this method to build a phase diagram of the zero-field metastable spin structures in FCGT, which will be critical for selecting the desired topologically-protected spin state for future studies to manipulate magnetism with stimuli such as electric current, electric field, mechanical strain, and more.

cond-mat.mtrl-sci↗

arXiv2026

Electric field switching of altermagnetic spin-splitting in multiferroic skyrmions

Magnetic skyrmions are localized magnetic structures that retain their shape and stability over time, thanks to their topological nature. Recent theoretical and experimental progress has laid the groundwork for understanding magnetic skyrmions characterized by negligible net magnetization and ultrafast dynamics. Notably, skyrmions emerging in materials with altermagnetism, a novel magnetic phase featuring lifted Kramers degeneracy-have remained unreported until now. In this study, we demonstrate that BiFeO3, a multiferroic renowned for its strong coupling between ferroelectricity and magnetism, can transit from a spin cycloid to a Neel-type skyrmion under antidamping spin-orbit torque at room temperature. Strikingly, the altermagnetic spin splitting within BiFeO3 skyrmion can be reversed through the application of an electric field, revealed via the Circular photogalvanic effect. This quasiparticle, which possesses a neutral topological charge, holds substantial promise for diverse applications-most notably, enabling the development of unconventional computing systems with low power consumption and magnetoelectric controllability.

cond-mat.mtrl-sci↗

arXiv2025

From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?

Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures. In parallel, reinforcement learning (RL) has broadened exploration and enabled precise multi-objective optimization in protein design. Yet whether RL can push PLMs beyond their pretraining priors to uncover latent sequence-structure-function rules remains unclear. We address this by pairing RL with PLMs across four domains: antimicrobial peptide design, kinase variant optimization, antibody engineering, and inverse folding. Using diverse RL algorithms and model classes, we ask if RL improves sampling efficiency and, more importantly, if it reveals capabilities not captured by supervised learning. Across benchmarks, RL consistently boosts success rates and sample efficiency. Performance follows a three-factor interaction: task headroom, reward fidelity, and policy capacity jointly determine gains. When rewards are accurate and informative, policies have sufficient capacity, and tasks leave room beyond supervised baselines, improvements scale; when rewards are noisy or capacity is constrained, gains saturate despite exploration. This view yields practical guidance for RL in protein design: prioritize reward modeling and calibration before scaling policy size, match algorithm and regularization strength to task difficulty, and allocate capacity where marginal gains are largest. Implementation is available at https://github.com/chq1155/RL-PLM.

cs.LG↗

arXiv2025

Half-filled metal and molecular-orbital-mediated pairing in cuprate

The cuprates exhibit anomalous momentum-space structure with antinodal gap and nodal arc in the underdoped regime, which evolves into a complete hole-type Fermi surface with a large Luttinger volume in the overdoped regime. The real-space electronic structure is also quite complex, as characterized by microscopic inhomogeneities and intertwined density wave orders. Here we show that doped holes in cuprate form localized electronic molecules consisting of 4a0 plaquettes, and each plaquette contains approximately two holes. The effective local doping level is thus around 1/8, which is sufficient to destroy the underlying AF order and more importantly, recovers the half-filled metallic state of the original CuO2 plane. The restored Fermi surface, hosting one hole per unit cell, is consistent with experimental results and satisfies the Luttinger theorem. We then construct the momentum-space structure of the half-filled metal by considering the real-space configuration of electronic molecules. We show that the electronic potential with 4a0 periodicity imposed by the plaquettes and the quantum size effect of electronic molecules obliterate the nested antinodal Fermi surface sheets, leaving behind short arcs with coherent quasiparticles around the node. We propose that two doped holes in each plaquette occupy the shared molecular orbital and form a spin singlet, which can mediate the pairing of itinerant holes on the remnant Fermi surface of the half-filled metal. The electric dipole moment between the molecular orbitals and the dopant ions may also provide a novel attractive interaction between itinerant holes. This phenomenological model for pair formation between itinerant holes on the half-filled Fermi surface mediated by localized molecular orbitals resolves several core issues concerning the mechanism of superconductivity in cuprates.

cond-mat.supr-con↗

arXiv2025

Electron-magnon coupling at the interface of a "twin-twisted" antiferromagnet

We identify a "twin-twist" angle in orthorhombic two-dimensional magnets that maximizes interlayer orbital overlap and enables strong interfacial coupling. Focusing on the van der Waals antiferromagnet CrSBr, we show that this twist angle, near 72 deg, aligns diagonal lattice vectors across the layers, enhancing the interlayer hopping that is spin-forbidden in pristine systems and orbital-forbidden in 90-deg-twisted samples. The enhanced hopping modifies the electronic structure and activates a novel mechanism for excitation of interfacial magnons. Using optical probes we discover that excitons on one side of the interface selectively excite magnons localized on the opposite side. We show that this cross-coupling phenomenon can be understood as a consequence of the spin-transfer torque as that arises as electrons tunnel across the twin-twisted interface. Our findings demonstrate that large-angle twisting in anisotropic 2D materials offers a powerful tool for engineering spin and charge transport through controlled interlayer hybridization, opening new avenues for twisted magnetism and strongly correlated moiré physics.

cond-mat.mes-hall↗

arXiv2025

Transformer-Based Neural Quantum Digital Twins for Many-Body Spectral Reconstruction and Adaptive Quantum-Annealing Schedule Design

We introduce Transformer-based Neural Quantum Digital Twins (Tx-NQDTs) to reconstruct the low-energy spectral evolution of many-body quantum systems along quantum-annealing paths, including ground- and first-excited-state energies, spectral gaps, and transition matrix elements, at efficient computational cost. Tx-NQDTs employ a graph-informed Transformer neural network trained to estimate the spectral information needed for annealing-schedule design. We integrate these estimates with an adaptive schedule-construction procedure guided by first-order adiabatic perturbation theory (FOAPT), which is used as a closed-system spectral diagnostic to allocate annealing time near predicted spectral bottlenecks. Experiments on a D-Wave quantum annealer ($N=10,15,20$ logical variables, with schedules represented by up to 12 control points) show that Tx-NQDT-informed schedules can improve empirical ground-state success probabilities relative to the default $20\,\mu\mathrm{s}$ linear schedule under the tested hardware conditions. The proposed schedules achieve success probabilities $2.2$--$11.7$ percentage points higher across the reported easy and hard subsets and outperform the default baseline in 44 of 60 cases. The results demonstrate the feasibility of using learned logical spectral information to automatically generate adaptive quantum-annealing schedules for practical hardware experiments.

quant-ph↗

arXiv2025

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable concepts but often struggle with performance and scalability. Conversely, post-hoc methods like Shapley values, while theoretically robust, are computationally expensive and resource-intensive. To bridge the gap between these two lines of research, we propose a novel method that combines their strengths, providing theoretically guaranteed self-interpretability for black-box models without compromising prediction accuracy. Specifically, we introduce a parameter-efficient pipeline, AutoGnothi, which integrates a small side network into the black-box model, allowing it to generate Shapley value explanations without changing the original network parameters. This side-tuning approach significantly reduces memory, training, and inference costs, outperforming traditional parameter-efficient methods, where full fine-tuning serves as the optimal baseline. AutoGnothi enables the black-box model to predict and explain its predictions with minimal overhead. Extensive experiments show that AutoGnothi offers accurate explanations for both vision and language tasks, delivering superior computational efficiency with comparable interpretability.

cs.LG↗

arXiv2025

Benchmarking of Quantum and Classical Computing in Large-Scale Dynamic Portfolio Optimization Under Market Frictions

Quantum computing is poised to transform the financial industry, yet its advantages over traditional methods have not been evidenced. As this technology rapidly evolves, benchmarking is essential to fairly evaluate and compare different computational strategies. This study presents a challenging yet solvable problem of large-scale dynamic portfolio optimization under realistic market conditions with frictions. We frame this issue as a Quadratic Unconstrained Binary Optimization (QUBO) problem, compatible with digital computing and ready for quantum computing, to establish a reliable benchmark. By applying the latest solvers to real data, we release benchmarks that help verify true advancements in dynamic trading strategies, either quantum or digital computing, ensuring that reported improvements in portfolio optimization are based on robust, transparent, and comparable metrics.

math.OC↗

arXiv2025

Spin frustration and unconventional spin twisting state in van der Waals ferromagnet/antiferromagnet heterostructures

Atomically flat surfaces of van der Waals (vdW) materials pave an avenue for addressing a long-standing fundamental issue of how a perfectly compensated antiferromagnet (AFM) surface frustrates a ferromagnetic (FM) overlayer in FM/AFM heterostructures. By revealing the AFM and FM spin structures separately in vdW Fe5GeTe2/NiPS3 heterostructures, we find that C-type in-plane AFM NiPS3 develops three equivalent AFM domains which are robust against external magnetic field and magnetic coupling with Fe5GeTe2. Consequently, spin frustration at the Fe5GeTe2/NiPS3 interface was shown to develop a perpendicular Fe5GeTe2 magnetization in the interfacial region that switches separately from the bulk of the Fe5GeTe2 magnetizations. In particular, we discover an unconventional spin twisting state that the Fe5GeTe2 spins twist from perpendicular direction near the interface to in-plane direction away from the interface in Fe5GeTe2/NiPS3. Our finding of the twisting spin texture is a unique property of spin frustration in van der Waals magnetic heterostructures.

cond-mat.mtrl-sci↗

arXiv2025

Hybrid Quantum Neural Networks with Amplitude Encoding: Advancing Recovery Rate Predictions

Recovery rate prediction plays a pivotal role in bond investment strategies by enhancing risk assessment, optimizing portfolio allocation, improving pricing accuracy, and supporting effective credit risk management. However, accurate forecasting remains challenging due to complex nonlinear dependencies, high-dimensional feature spaces, and limited sample sizes-conditions under which classical machine learning models are prone to overfitting. We propose a hybrid Quantum Machine Learning (QML) model with Amplitude Encoding, leveraging the unitarity constraint of Parametrized Quantum Circuits (PQC) and the exponential data compression capability of qubits. We evaluate the model on a global recovery rate dataset comprising 1,725 observations and 256 features from 1996 to 2023. Our hybrid method significantly outperforms both classical neural networks and QML models using Angle Encoding, achieving a lower Root Mean Squared Error (RMSE) of 0.228, compared to 0.246 and 0.242, respectively. It also performs competitively with ensemble tree methods such as XGBoost. While practical implementation challenges remain for Noisy Intermediate-Scale Quantum (NISQ) hardware, our quantum simulation and preliminary results on noisy simulators demonstrate the promise of hybrid quantum-classical architectures in enhancing the accuracy and robustness of recovery rate forecasting. These findings illustrate the potential of quantum machine learning in shaping the future of credit risk prediction.

q-fin.CP↗