arXiv subjects

Mingyu Xu

Publications and source records attributed to Mingyu Xu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Superconductivity suppression and bilayer decoupling in Pr substituted YBa$_2$Cu$_3$O$_{7-δ}$

The mechanism behind superconductivity suppression induced by Pr substitutions in YBa$_2$Cu$_3$O$_{7-δ}$ (YBCO) has been a mystery since its discovery: in spite of being isovalent to Y$^{3+}$ with a small magnetic moment, it is the only rare-earth element that has a dramatic impact on YBCO's superconducting properties. Using angle-resolved photoemission spectroscopy (ARPES) and DFT+$U$ calculations, we uncover how Pr substitution modifies the low-energy electronic structure of YBCO. Contrary to the prevailing Fehrenbacher-Rice (FR) and Liechtenstein-Mazin (LM) models, the low energy electronic structure contains no signature of any $f$-electron hybridization or new states. Yet, strong electron doping is observed primarily on the antibonding Fermi surface. Meanwhile, we reveal major electronic structure modifications to Cu-derived states with increasing Pr substitution: a pronounced CuO$_2$ bilayer decoupling and an enhanced CuO chain hopping, implying indirect electron-release pathways beyond simple 4$f$ state ionization. Our results challenge the long-standing FR/LM mechanism and establish Pr substituted YBCO as a potential platform for exploring correlation-driven phenomena in coupled 1D-2D systems.

cond-mat.supr-con↗

arXiv2025

IRNet: Iterative Refinement Network for Noisy Partial Label Learning

Partial label learning (PLL) is a typical weakly supervised learning, where each sample is associated with a set of candidate labels. Its basic assumption is that the ground-truth label must be in the candidate set, but this assumption may not be satisfied due to the unprofessional judgment of annotators. Therefore, we relax this assumption and focus on a more general task, noisy PLL, where the ground-truth label may not exist in the candidate set. To address this challenging task, we propose a novel framework called ``Iterative Refinement Network (IRNet)'', aiming to purify noisy samples through two key modules (i.e., noisy sample detection and label correction). To achieve better performance, we exploit smoothness constraints to reduce prediction errors in these modules. Through theoretical analysis, we prove that IRNet is able to reduce the noise level of the dataset and eventually approximate the Bayes optimal classifier. Meanwhile, IRNet is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on multiple benchmark datasets show that IRNet outperforms state-of-the-art approaches on noisy PLL. Our source code is available at: https://github.com/zeroQiaoba/IRNet.

cs.CV↗

arXiv2025

Mesoscopic Helices of Polar Domains in a Quadruple Perovskite

A significant effort in condensed matter physics is dedicated to the search for exotic arrangements of electric dipoles in crystals. Non-collinear dipolar arrangements mimicking magnetic spin textures, such as polar vortices and skyrmions, have been realized, but others, like helices of dipoles, have remained elusive. While earlier work claimed the presence of a helical dipole modulation in ferroelectric BiCu$_{x}$Mn$_{7-x}$O$_{12}$, our results rule out such a structure, motivating a renewed search for helical textures. Using atomic-resolution imaging, we report a novel form of helical order in which polar domains self-organize into a mesoscopic helical pattern: from domain to domain, polarization rotation follows a consistent handedness. Both right- and left-handed chirality emerging from this helical ordering are observed. This discovery establishes mesoscopic ordering as novel mechanism for inducing helical textures, and hence chirality, in ferroelectric crystals, paralleling the efforts in liquid crystals and supramolecular assemblies.

cond-mat.mes-hall↗

arXiv2025

Strain-tunability of the multipolar Berry curvature in altermagnet MnTe

The anomalous Hall effect describes the generation of a transverse voltage by a longitudinal current even in the absence of an external magnetic field. While typically observed in ferromagnets, it has also been predicted to arise in altermagnets, materials characterized by rotational symmetries that enable broken time reversal symmetry despite compensated collinear magnetic ordering. These symmetries enforce band (anti)crossings that can generate significant contributions to the Berry curvature that drives the anomalous Hall effect. This Berry curvature is predicted to exhibit a characteristic multipolar order, resulting in a symmetry-enforced distribution at or near net compensation which is highly sensitive to perturbations that distort this balance. However, exploring the predicted multipolar Berry curvature of altermagnets and its reversible manipulation remains challenging. Here, we demonstrate evidence for the multipolar nature of the altermagnetic Berry curvature in MnTe by tuning the anomalous Hall effect via uniaxial stress. Upon straining, the magnitude of the anomalous Hall conductivity changes and, at a critical strain of 0.14%, the sign is reversed. Symmetry analysis and density functional theory calculations reveal that this tunability is a direct consequence of the altermagnetic multipolar Berry curvature. Our results provide insight into the role of crystal and magnetic symmetries in the realization of higher-order Berry curvature distributions and their unique tunability.

cond-mat.mtrl-sci↗

arXiv2025

Large Anomalous and Topological Hall Effect and Nernst Effect in a Dirac Kagome Magnet Fe3Ge

The search for kagome magnets with unconventional magnetic and electronic properties has gained significant attention in recent years. We report the magnetic, electronic, and thermoelectric properties of Fe3Ge single crystals, where the Fe atoms form a slightly distorted kagome lattice. Fe3Ge exhibits a large anomalous Hall effect and anomalous Nernst effect. The anomalous transverse thermoelectric conductivity reaches about 4.6 A m^-1 K^-1, exceeding values reported for conventional ferromagnets and most topological ferromagnets. First-principles calculations indicate that these transport responses are primarily governed by intrinsic mechanisms, highlighting the dominant role of Berry curvature arising from massive Dirac gaps in momentum space. In addition, we observe a topological Hall resistivity of about 0.9 microOhm cm and a topological Nernst coefficient of 1.2 microvolt K^-1, which are attributed to the Berry phase associated with field-induced scalar spin chirality. These findings demonstrate the combined influence of Berry phases in both momentum and real space, establishing Fe3Ge as a promising candidate for room-temperature transverse thermoelectric applications.

cond-mat.mtrl-sci↗

arXiv2025

Many-body delocalization with a two-dimensional 70-qubit superconducting quantum simulator

Quantum many-body systems with sufficiently strong disorder can exhibit a non-equilibrium phenomenon, known as the many-body localization (MBL), which is distinct from conventional thermalization. While the MBL regime has been extensively studied in one dimension, its existence in higher dimensions remains elusive, challenged by the avalanche instability. Here, using a 70-qubit two-dimensional (2D) superconducting quantum simulator, we experimentally explore the robustness of the MBL regime in controlled finite-size 2D systems. We observe that the decay of imbalance becomes more pronounced with increasing system sizes, scaling up from 21, 42 to 70 qubits, with a relatively large disorder strength, and for the first time, provide an evidence for the many-body delocalization in 2D disordered systems. Our experimental results are consistent with the avalanche theory that predicts the instability of MBL regime beyond one spatial dimension. This work establishes a scalable platform for probing high-dimensional non-equilibrium phases of matter and their finite-size effects using superconducting quantum circuits.

quant-ph↗

arXiv2025

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation

Large language models (LLMs) have gained extended context windows through scaling positional encodings and lightweight continual pre-training. However, this often leads to degraded performance on short-text tasks, while the reasons for this degradation remain insufficiently explored. In this work, we identify two primary factors contributing to this issue: distribution drift in hidden states and attention scores, and catastrophic forgetting during continual pre-training. To address these challenges, we propose Long Context Pre-training with Restoration Distillation (LongReD), a novel approach designed to mitigate short-text performance degradation through minimizing the distribution discrepancy between the extended and original models. Besides training on long texts, LongReD distills the hidden state of selected layers from the original model on short texts. Additionally, LongReD also introduces a short-to-long distillation, aligning the output distribution on short texts with that on long texts by leveraging skipped positional indices. Experiments on common text benchmarks demonstrate that LongReD effectively preserves the model's short-text performance while maintaining comparable or even better capacity to handle long texts than baselines. Our code is available at https://github.com/RUCAIBox/LongReD.

cs.CL↗

arXiv2025

Understanding Transformer from the Perspective of Associative Memory

In this paper, we share our reflections and insights on understanding Transformer architectures through the lens of associative memory--a classic psychological concept inspired by human cognition. We start with the basics of associative memory (think simple linear attention) and then dive into two dimensions: Memory Capacity: How much can a Transformer really remember, and how well? We introduce retrieval SNR to measure this and use a kernel perspective to mathematically reveal why Softmax Attention is so effective. We also show how FFNs can be seen as a type of associative memory, leading to insights on their design and potential improvements. Memory Update: How do these memories learn and evolve? We present a unified framework for understanding how different Transformer variants (like DeltaNet and Softmax Attention) update their "knowledge base". This leads us to tackle two provocative questions: 1. Are Transformers fundamentally limited in what they can express, and can we break these barriers? 2. If a Transformer had infinite context, would it become infinitely intelligent? We want to demystify Transformer architecture, offering a clearer understanding of existing designs. This exploration aims to provide fresh insights and spark new avenues for Transformer innovation.

cs.LG↗

arXiv2025

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN

Recently, models such as OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable performance on complex reasoning tasks through Long Chain-of-Thought (Long-CoT) reasoning. Although distilling this capability into student models significantly enhances their performance, this paper finds that fine-tuning LLMs with full parameters or LoRA with a low rank on long CoT data often leads to Cyclical Reasoning, where models repeatedly reiterate previous inference steps until the maximum length limit. Further analysis reveals that smaller differences in representations between adjacent tokens correlates with a higher tendency toward Cyclical Reasoning. To mitigate this issue, this paper proposes Shift Feedforward Networks (Shift-FFN), a novel approach that edits the current token's representation with the previous one before inputting it to FFN. This architecture dynamically amplifies the representation differences between adjacent tokens. Extensive experiments on multiple mathematical reasoning tasks demonstrate that LoRA combined with Shift-FFN achieves higher accuracy and a lower rate of Cyclical Reasoning across various data sizes compared to full fine-tuning and standard LoRA. Our data and code are available at https://anonymous.4open.science/r/Shift-FFN

cs.CL↗

arXiv2025

A general and modular approach to solid-state integration and readout of zero-dimensional quantum systems

Here, we present an all-electrical readout mechanism for quasi-0D quantum states (0D-QS) such as point defects, adatoms and molecules, that is modular and general, providing an approach that is amenable to scaling and integration with other solid-state quantum technologies. Our approach relies on the crea-tion of high-quality tunnel junctions via the mechanical exfoliation and stacking of multi-layer gra-phene (MLG) and hexagonal boron nitride (hBN) to encapsulate the target system in an MLG/hBN/0D-QS/hBN/MLG heterostructure. This structure allows for all-electronic spectroscopy and readout of candidate systems through a combination of coulomb and spin-blockade. As a proof of principle, we demonstrate electronic tunneling spectroscopy of point defects in hBN and the molecular qubit vanadyl phthalocyanine (VOPc). Our approach demonstrates a new pathway for the incorporation of molecules and atomic defects into solid-state quantum devices and circuits along with a readout scheme that does not rely on highly-constrained optical processes for photonic readout.

cond-mat.mtrl-sci↗

arXiv2025

Baichuan-M1: Pushing the Medical Capability of Large Language Models

The current generation of large language models (LLMs) is typically designed for broad, general-purpose applications, while domain-specific LLMs, especially in vertical fields like medicine, remain relatively scarce. In particular, the development of highly efficient and practical LLMs for the medical domain is challenging due to the complexity of medical knowledge and the limited availability of high-quality data. To bridge this gap, we introduce Baichuan-M1, a series of large language models specifically optimized for medical applications. Unlike traditional approaches that simply continue pretraining on existing models or apply post-training to a general base model, Baichuan-M1 is trained from scratch with a dedicated focus on enhancing medical capabilities. Our model is trained on 20 trillion tokens and incorporates a range of effective training methods that strike a balance between general capabilities and medical expertise. As a result, Baichuan-M1 not only performs strongly across general domains such as mathematics and coding but also excels in specialized medical fields. We have open-sourced Baichuan-M1-14B, a mini version of our model, which can be accessed through the following links.

cs.CL↗

arXiv2024

Giant Nernst Angle in Self-Intercalated van der Waals Magnet Cr$_{1.25}$Te$_2$

The discovery of two-dimensional van der Waals (vdW) magnetic materials has propelled advancements in technological devices. The Nernst effect, which generates a transverse electric voltage in the presence of a longitudinal thermal gradient, shows great promise for thermoelectric applications. In this work, we report the electronic and thermoelectric transport properties of Cr$_{1.25}$Te$_2$, a layered self-intercalated vdW material which exhibits an antiferromagnetic ordering at TN ~ 191 K followed by a ferromagnetic-like phase transition at TC ~171 K. We observe a prominent topological Hall effect and topological Nernst effect between TC and TN, which is ascribable to non-coplanar spin textures inducing a real-space Berry phase due to competing ferromagnetic and antiferromagnetic interactions. Furthermore, we show that Cr$_{1.25}$Te$_2$ exhibits a substantial anomalous Nernst effect, featuring a giant Nernst angle of ~37% near TC and a maximum Nernst thermoelectric coefficient of 0.52 uV/K. These results surpass those of conventional ferromagnets and other two-dimensional vdW materials, highlighting Cr$_{1.25}$Te$_2$ as a promising candidate for advanced thermoelectric devices based on the Nernst effect.

cond-mat.mtrl-sci↗

arXiv2024

KV Shifting Attention Enhances Language Modeling

The current large language models are mainly based on decode-only structure transformers, which have great in-context learning (ICL) capabilities. It is generally believed that the important foundation of its ICL capability is the induction heads mechanism, which requires at least two layers attention. In order to more efficiently implement the ability of the model's induction, we revisit the induction heads mechanism and proposed a KV shifting attention. We theoretically prove that the KV shifting attention reducing the model's requirements for the depth and width of the induction heads mechanism. Our experimental results demonstrate that KV shifting attention is beneficial to learning induction heads and language modeling, which lead to better performance or faster convergence from toy models to the pre-training models with more than 10 B parameters.

cs.CL↗

arXiv2024

Two Kinds of Learning Algorithms for Continuous-Time VWAP Targeting Execution

The optimal execution problem has always been a continuously focused research issue, and many reinforcement learning (RL) algorithms have been studied. In this article, we consider the execution problem of targeting the volume weighted average price (VWAP) and propose a relaxed stochastic optimization problem with an entropy regularizer to encourage more exploration. We derive the explicit formula of the optimal policy, which is Gaussian distributed, with its mean value being the solution to the original problem. Extending the framework of continuous RL to processes with jumps, we provide some theoretical proofs for RL algorithms. First, minimizing the martingale loss function leads to the optimal parameter estimates in the mean-square sense, and the second algorithm is to use the martingale orthogonality condition. In addition to the RL algorithm, we also propose another learning algorithm: adaptive dynamic programming (ADP) algorithm, and verify the performance of both in two different environments across different random seeds. Convergence of all algorithms has been verified in different environments, and shows a larger advantage in the environment with stronger price impact. ADP is a good choice when the agent fully understands the environment and can estimate the parameters well. On the other hand, RL algorithms do not require any model assumptions or parameter estimation, and are able to learn directly from interactions with the environment.

math.OC↗

arXiv2024

Tetragonal BaCoO$_3$: A Co$^{4+}$ Ferromagnetic Mott Insulator with Inverted Spin Crossover

The interplay between crystal electric field splitting of d states and Hund's rule exchange energy in cobalt-based perovskites offers a promising avenue for inducing spin-state transitions. This study reports a new body-centered tetragonal (BCT) phase of BaCoO$_3$ (BCT-BaCoO$_3$), synthesized under high pressure (15 GPa) and high temperature (1200 °C) conditions. BCT-BaCoO$_3$ adopts a double perovskite structure of EuTiO$_3$-type (space group I4/mcm, #140), confirmed by high-resolution scanning transmission electron microscopy. X-ray photoelectron spectroscopy reveals a rare Co$^{4+}$ valence state. Magnetization and X-ray absorption measurements reveal a low-spin to high-spin transition that takes place between 200 and 300 K. While spin crossovers are relatively common among common oxides, the one observed in BCT-BaCoO$_3$ is remarkable in that it proceeds in the opposite direction from conventional spin transitions. BCT-BaCoO$_3$ exhibits a low-spin (S = 1/2) state at high temperatures and transitions to a high-spin (S = 5/2) state at low temperatures. Within the high-spin state, hard ferromagnetic order onsets at T$_C$ = 107 K. Electrical resistivity indicates weak magnetoresistance and insulating behavior. Overall, BCT-BaCoO$_3$ presents an exceptional model for the exploration of spin-state transitions and the study of Co spin states in cobalt-based perovskites.

cond-mat.mtrl-sci↗

arXiv2024

Pressure-Induced Phase Transitions in Bilayer La$_3$Ni$_2$O$_7$

La$_3$Ni$_2$O$_7$ exists in two polymorphs: an unconventional structure with alternating layers of single- and triple-layered nickel-oxygen octahedra, and a classical double-layered Ruddlesden-Popper phase. In this study, we report the growth of single crystals of classical double-layered La$_3$Ni$_2$O$_7$ using the floating zone method. Structural characterization under pressures up to 15.4 GPa reveals a gradual transition from orthorhombic to tetragonal symmetry near 12 GPa. Additionally, we present pressure and field-dependent electrical resistance measurements under pressures as high as 27.4 GPa, from which we construct a phase diagram.

cond-mat.mtrl-sci↗

arXiv2024

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. However, in this study, we discovered that many layers of LLMs exhibit high similarity, and some layers play a negligible role in network functionality. Based on this observation, we define a metric called Block Influence (BI) to gauge the significance of each layer in LLMs. We then propose a straightforward pruning approach: layer removal, in which we directly delete the redundant layers in LLMs based on their BI scores. Experiments demonstrate that our method, which we call ShortGPT, significantly outperforms previous state-of-the-art (SOTA) methods in model pruning. Moreover, ShortGPT is orthogonal to quantization-like methods, enabling further reduction in parameters and computation. The ability to achieve better results through simple layer removal, as opposed to more complex pruning techniques, suggests a high degree of redundancy in the model architecture.

cs.CL↗

arXiv2024

SVFAP: Self-supervised Video Facial Affect Perceiver

Video-based facial affect analysis has recently attracted increasing attention owing to its critical role in human-computer interaction. Previous studies mainly focus on developing various deep learning architectures and training them in a fully supervised manner. Although significant progress has been achieved by these supervised methods, the longstanding lack of large-scale high-quality labeled data severely hinders their further improvements. Motivated by the recent success of self-supervised learning in computer vision, this paper introduces a self-supervised approach, termed Self-supervised Video Facial Affect Perceiver (SVFAP), to address the dilemma faced by supervised methods. Specifically, SVFAP leverages masked facial video autoencoding to perform self-supervised pre-training on massive unlabeled facial videos. Considering that large spatiotemporal redundancy exists in facial videos, we propose a novel temporal pyramid and spatial bottleneck Transformer as the encoder of SVFAP, which not only largely reduces computational costs but also achieves excellent performance. To verify the effectiveness of our method, we conduct experiments on nine datasets spanning three downstream tasks, including dynamic facial expression recognition, dimensional emotion recognition, and personality recognition. Comprehensive results demonstrate that SVFAP can learn powerful affect-related representations via large-scale self-supervised pre-training and it significantly outperforms previous state-of-the-art methods on all datasets. Code is available at https://github.com/sunlicai/SVFAP.

cs.CV↗