Searcharxiv⌕ Search

arXiv subjects

Yu Song

Publications and source records attributed to Yu Song.

At least 37 records · Page 2Linked to original sources
arXiv2026

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education

Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social trajectories are irreversibly shaped, while real-world trials are slow, ethically constrained, and institutionally locked. LLM-based educational simulators have emerged as a potential remedy, but many still collapse learning into persona-conditioned role-play and, when optimized only to reproduce existing classrooms, can structurally penalize the institutional novelty that pedagogical reform requires. In this work, we introduce AgentSchool, an LLM-driven multi-agent simulator that models learning as state transition rather than prompted behavior. AgentSchool couples cognitively growable student agents -- equipped with weighted subject knowledge graphs, thinking-workflow pools, and explicit misconceptions -- with adaptive teacher agents that plan, scaffold, and reflect along the Zone of Proximal Development, embedded in a configurable scenery generator that situates instruction within both formal and informal learning fields, and a multi-scale simulator that decouples interaction scale, temporal granularity, and simulation duration. Experiments show that structured student agents produce more differentiated mastery and misconception traces than a baseline simulator, while teacher-agent comparisons show backbone-dependent patterns consistent with ZPD-informed adaptation. Further, AgentSchool generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence consistent with classroom social theories. Beyond its role as an educational research instrument, AgentSchool frames education as a socially meaningful testbed for long-horizon memory, multi-agent coordination, and future institutional reasoning under organizational pressure.

cs.AI↗
arXiv2026

Observation of hidden altermagnetism in Cs$_{1-δ}$V$_2$Te$_2$O

Altermagnets are characterized by anisotropic band/spin splittings in momentum space, dictated by their spin-space group symmetries. However, the real-space modulations of altermagnetism are often neglected and have not been explored experimentally. Here we combine neutron diffraction, angle-resolved photoemission spectroscopy (ARPES), spin-resolved ARPES and density functional theory to demonstrate that Cs$_{1-δ}$V$_2$Te$_2$O realizes a spatially modulated form of altermagnetism, i.e., hidden altermagnetism. Such a state in Cs$_{1-δ}$V$_2$Te$_2$O results from its G-type antiferromagnetism and two-dimensional electronic states, allowing for the development of spatially alternating altermagnetic layers, whose local spin polarizations are directly verified by spin-resolved ARPES measurements. Our experimental discovery of hidden altermagnetism broadens the scope of unconventional magnetism and opens routes to exploring emergent phenomena from real-space modulations of altermagnetic order.

cond-mat.mtrl-sci↗
arXiv2026

Antiferromagnetic Dimers in the Parent Phase of a Correlated Kagome Superconductor

Kagome metals are prone to charge-density wave (CDW), magnetic, and superconducting phases, with their flat electronic band conducive for correlated physics. In contrast to the weakly correlated $A$V$_3$Sb$_5$ ($A$ = K, Rb, Cs) kagome metals with a $2\times2$ CDW, CsCr$_3$Sb$_5$ is a correlated metal with a flat band close to the Fermi level, and exhibits a $4\times1$ CDW intertwined with magnetic order. Under pressure, the intertwined orders are suppressed and give way to a dome of superconductivity that emerges from a non-Fermi liquid normal state. Here, we solve the crystal structure of the $4\times 1$ CDW state in CsCr$_3$Sb$_5$, and show it consists of Cr dimers separated by Cr chains. First-principles calculations show the dominant exchange interaction is antiferromagnetic within the dimers, while the intra-chain and dimer-chain couplings are much weaker. The CDW transition of CsCr$_3$Sb$_5$ is found to be more strongly first-order than those in $A$V$_3$Sb$_5$, without significant soft phonons or diffuse scattering above the CDW transition temperature. These findings suggest that fluctuating antiferromagnetic dimers may play a major role in the electron pairing of superconducting CsCr$_3$Sb$_5$.

cond-mat.str-el↗
arXiv2026

A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction

Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit them from capturing discriminative features and recognizing small objects. In this work, we propose Asymptotic Content-Aware Pyramid Attention Network (A3-FPN), to augment multi-scale feature representation via the asymptotically disentangled framework and content-aware attention modules. Specifically, A3-FPN employs a horizontally-spread column network that enables asymptotically global feature interaction and disentangles each level from all hierarchical representations. In feature fusion, it collects supplementary content from the adjacent level to generate position-wise offsets and weights for context-aware resampling, and learns deep context reweights to improve intra-category similarity. In feature reassembly, it further strengthens intra-scale discriminative feature learning and reassembles redundant features based on information content and spatial variation of feature maps. Extensive experiments on MS COCO, VisDrone2019-DET and Cityscapes demonstrate that A3-FPN can be easily integrated into state-of-the-art CNN and Transformer-based architectures, yielding remarkable performance gains. Notably, when paired with OneFormer and Swin-L backbone, A3-FPN achieves 49.6 mask AP on MS COCO and 85.6 mIoU on Cityscapes. Codes are available at https://github.com/mason-ching/A3-FPN.

cs.CV↗
arXiv2026

Soft Phonon Charge-Density Wave Formation in the Kagome Metal KV$_3$Sb$_5$

A range of of unusual emergent behaviors have been reported in the charge-density wave (CDW) state of the $A$V$_3$Sb$_5$ ($A=~$K, Rb, Cs) kagome metals, including a CDW formation process without soft phonons, which points to an unconventional CDW mechanism. Here, we use inelastic x-ray scattering to show that the CDW in KV$_3$Sb$_5$ forms via phonons that soften to zero energy at the CDW ordering vector ($L$-point) around $T_{\rm CDW}=78$~K. The intensity of soft phonons exhibit a remarkable in-plane anisotropy, extending over a much larger momentum range along $L$-$A$ relative to $L$-$H$, which leads to diffuse scattering common among $A$V$_3$Sb$_5$. Using first-principles calculations, we find that the momentum-dependent electron-phonon coupling (EPC) is peaked at $L$ and exhibits the same in-plane anisotropy as the phonon softening. Conversely, the electronic susceptibility is not peaked at $L$ and shows the opposite in-plane anisotropy. Our findings favor momentum-dependent EPC as the driving mechanism of the CDW in KV$_3$Sb$_5$, with a CDW formation process similar to that of transition metal dichalcogenides.

cond-mat.supr-con↗
arXiv2026

Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek

The advent of Computer-Aided Design (CAD) generative modeling will significantly transform the design of industrial products. The recent research endeavor has extended into the realm of Large Language Models (LLMs). In contrast to fine-tuning methods, training-free approaches typically utilize the advanced closed-source LLMs, thereby offering enhanced flexibility and efficiency in the development of AI agents for generating CAD parametric models. However, the substantial cost and limitations of local deployment of the top-tier closed-source LLMs pose challenges in practical applications. The Seek-CAD is the pioneer exploration of locally deployed open-source inference LLM DeepSeek-R1 for CAD parametric model generation with a training-free methodology. This study is the first investigation to incorporate both visual and Chain-of-Thought (CoT) feedback within the self-refinement mechanism for generating CAD models. Specifically, the initial generated parametric CAD model is rendered into a sequence of step-wise perspective images, which are subsequently processed by a Vision Language Model (VLM) alongside the corresponding CoTs derived from DeepSeek-R1 to assess the CAD model generation. Then, the feedback is utilized by DeepSeek-R1 to refine the initial generated model for the next round of generation. Moreover, we present an innovative 3D CAD model dataset structured around the SSR (Sketch, Sketch-based feature, and Refinements) triple design paradigm. This dataset encompasses a wide range of CAD commands, thereby aligning effectively with industrial application requirements and proving suitable for the generation of LLMs. Extensive experiments validate the effectiveness of Seek-CAD under various metrics.

cs.CV↗
arXiv2026

Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modeling

Computer-Aided Design (CAD) generative modeling has a strong and long-term application in the industry. Recently, the parametric CAD sequence as the design logic of an object has been widely mined by sequence models. However, the industrial CAD models, especially in component objects, are fine-grained and complex, requiring a longer parametric CAD sequence to define. To address the problem, we introduce Mamba-CAD, a self-supervised generative modeling for complex CAD models in the industry, which can model on a longer parametric CAD sequence. Specifically, we first design an encoder-decoder framework based on a Mamba architecture and pair it with a CAD reconstruction task for pre-training to model the latent representation of CAD models; and then we utilize the learned representation to guide a generative adversarial network to produce the fake representation of CAD models, which would be finally recovered into parametric CAD sequences via the decoder of MambaCAD. To train Mamba-CAD, we further create a new dataset consisting of 77,078 CAD models with longer parametric CAD sequences. Comprehensive experiments are conducted to demonstrate the effectiveness of our model under various evaluation metrics, especially in the generation length of valid parametric CAD sequences. The code and dataset can be achieved from https://github.com/Sunny-Hack/Code-for-Mamba-CAD-AAAI-2025-.

cs.CV↗
arXiv2026

Altermagnetic Even-Odd Effects in CsV$_2$Te$_2$O Josephson Junctions

The interplay between conventional superconductivity and unconventional magnetism offers an exciting platform for realizing exotic superconducting phenomena. Here, we investigate Josephson effects in planar and vertical junctions based on CsV$_2$Te$_2$O-family materials, which host hidden $d$-wave altermagnetism with G-type antiferromagnetic order. In monolayer-based planar junctions, the quasi-1D, nearly flat, spin-polarized bands of the altermagnet, when coupled to $s$-wave superconductors, produce a \textit{fully} spin-polarized supercurrent with strong directional anisotropy -- a spin-selective Josephson effect. In multilayers, we uncover an \textit{altermagnetic even-odd effect}: spin-polarized supercurrents persist only in odd-layer planar junctions but cancel exactly in even layers. Thus, layer parity acts as a switch for spin-polarized supercurrent. In vertical junctions, odd-layer barriers enhance equal-spin triplet transport while even layers favor opposite-spin transport, yielding a robust period-two oscillation in the total supercurrent with layer number. These layer-parity-dependent responses represent a general even-odd effect in hidden altermagnets, applicable to diverse magnetic and transport phenomena.

cond-mat.supr-con↗
arXiv2026

Hierarchical Audio-Visual-Proprioceptive Fusion for Precise Robotic Manipulation

Existing robotic manipulation methods primarily rely on visual and proprioceptive observations, which may struggle to infer contact-related interaction states in partially observable real-world environments. Acoustic cues, by contrast, naturally encode rich interaction dynamics during contact, yet remain underexploited in current multimodal fusion literature. Most multimodal fusion approaches implicitly assume homogeneous roles across modalities, and thus design flat and symmetric fusion structures. However, this assumption is ill-suited for acoustic signals, which are inherently sparse and contact-driven. To achieve precise robotic manipulation through acoustic-informed perception, we propose a hierarchical representation fusion framework that progressively integrates audio, vision, and proprioception. Our approach first conditions visual and proprioceptive representations on acoustic cues, and then explicitly models higher-order cross-modal interactions to capture complementary dependencies among modalities. The fused representation is leveraged by a diffusion-based policy to directly generate continuous robot actions from multimodal observations. The combination of end-to-end learning and hierarchical fusion structure enables the policy to exploit task-relevant acoustic information while mitigating interference from less informative modalities. The proposed method has been evaluated on real-world robotic manipulation tasks, including liquid pouring and cabinet opening. Extensive experiment results demonstrate that our approach consistently outperforms state-of-the-art multimodal fusion frameworks, particularly in scenarios where acoustic cues provide task-relevant information not readily available from visual observations alone. Furthermore, a mutual information analysis is conducted to interpret the effect of audio cues in robotic manipulation via multimodal fusion.

cs.RO↗
arXiv2026

Hybrid Black Hole and Disk-Driven Jets: Steady Axisymmetric Ideal MHD Modeling

Improved observational precision in relativistic jets has underscored the need for tractable theoretical models. In this study, we construct a semi-analytical hybrid jet model that incorporates both black hole-driven and disk-driven components within the framework of steady, axisymmetric, ideal MHD. We derive a condition that determines the launching sites of cold outflows, introducing a new constraint on the magnetic field configuration threading the accretion disk. Using the Bernoulli equation and critical point analysis, we derive flow solutions along various magnetic field lines. Our hybrid jet model shows that discontinuities in field-line angular velocity lead to clear velocity shear and density jumps at the interface between the two jet components. These features are accompanied by localized enhancements in velocity and density, potentially explaining the observed limb-brightening.

astro-ph.HE↗
arXiv2026

Towards Agentic Intelligence for Materials Science

The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in discovery requires moving beyond task-isolated, fine-tuned models toward agentic systems that plan, act, and learn across the full discovery loop. This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining, through domain adaptation and instruction tuning, to goal-conditioned agents interfacing with simulation and experimental platforms. Unlike prior reviews, we treat the entire process as an end-to-end system to be optimized for tangible discovery outcomes rather than proxy benchmarks. This perspective allows us to trace how upstream design choices-such as data curation and training objectives-can be aligned with downstream experimental success through effective credit assignment. To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science. We then analyze the field through two focused lenses: From the AI perspective, the survey details LLM strengths in pattern recognition, predictive analytics, and natural language processing for literature mining, materials characterization, and property prediction; from the materials science perspective, it highlights applications in materials design, process optimization, and the acceleration of computational workflows via integration with external tools (e.g., DFT, robotic labs). Finally, we contrast passive, reactive approaches with agentic design, cataloging current contributions while motivating systems that pursue long-horizon goals with autonomy, memory, and tool use. This survey charts a practical roadmap towards autonomous, safety-aware LLM agents aimed at discovering novel and useful materials.

cond-mat.mtrl-sci↗
arXiv2026

Quasi-one-dimensional spin excitations in the iron pnictide NaFe$_{0.53}$Cu$_{0.47}$As

Spectroscopic measurements in model one-dimensional (1D) correlated systems offer insights for understanding their two-dimensional counterparts, which include the cuprate and iron pnictide/chalcogenide superconductors. A major challenge is the identification of such correlated systems with dominantly 1D physics. In this work, inelastic neutron scattering measurements on NaFe$_{0.53}$Cu$_{0.47}$As single crystal directly reveal quasi-1D spin excitations, resulting from atomic order that lead to magnetic Fe and nonmagnetic Cu chains. The dominant exchange interaction is antiferromagnetic along the chain ($SJ_{\rm \parallel}\approx90.1(3)$~meV), whereas the inter-chain couplings are much weaker ($SJ_{\rm \perp}\approx-2.4(1)$~meV and $SJ_{\rm c}\approx0.15(5)$~meV). The quasi-1D spin excitations in NaFe$_{0.53}$Cu$_{0.47}$As stem from both the Néel and stripe vectors, with Néel excitations sensitive to Fe impurities on the Cu site. The spin excitations in quasi-1D NaFe$_{0.53}$Cu$_{0.47}$As and quasi-2D FeSe exhibit a striking resemblance, suggesting a common origin for their coexistent stripe and Néel excitations. Our findings demonstrate magnetic dilution in NaFeAs leads to dimension reduction of its magnetic degree of freedom, presenting a strategy for discovering low-dimensional quantum materials.

cond-mat.str-el↗
arXiv2026

EduResearchBench: A Hierarchical Atomic Task Decomposition Benchmark for Full-Lifecycle Educational Research

While Large Language Models (LLMs) are reshaping the paradigm of AI for Social Science (AI4SS), rigorously evaluating their capabilities in scholarly writing remains a major challenge. Existing benchmarks largely emphasize single-shot, monolithic generation and thus lack the fine-grained assessments required to reflect complex academic research workflows. To fill this gap, we introduce EduResearchBench, the first comprehensive evaluation platform dedicated to educational academic writing. EduResearchBench is built upon our Hierarchical Atomic Task Decomposition (HATD) framework, which decomposes an end-to-end research workflow into six specialized research modules (e.g., Quantitative Analysis, Qualitative Research, and Policy Research) spanning 24 fine-grained atomic tasks. This taxonomy enables an automated evaluation pipeline that mitigates a key limitation of holistic scoring, where aggregate scores often obscure specific capability bottlenecks, and instead provides fine-grained, diagnostic feedback on concrete deficiencies. Moreover, recognizing the high cognitive load inherent in scholarly writing, we propose a curriculum learning strategy that progressively builds competence from foundational skills to complex methodological reasoning and argumentation. Leveraging 55K raw academic samples, we curate 11K high-quality instruction pairs to train EduWrite, a specialized educational scholarly writing model. Experiments show that EduWrite (30B) substantially outperforms larger general-purpose models (72B) on multiple core metrics, demonstrating that in vertical domains, data quality density and hierarchically staged training curricula are more decisive than parameter scale.

cs.CL↗
arXiv2026

Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities

Multimodal recommendation has emerged as a mainstream paradigm, typically leveraging text and visual embeddings extracted from pre-trained models such as Sentence-BERT, Vision Transformers, and ResNet. This approach is founded on the intuitive assumption that incorporating multimodal embeddings can enhance recommendation performance. However, despite its popularity, this assumption lacks comprehensive empirical verification. This presents a critical research gap. To address it, we pose the central research question of this paper: Are multimodal embeddings truly beneficial for recommendation? To answer this question, we conduct a large-scale empirical study examining the role of text and visual embeddings in modern multimodal recommendation models, both as a whole and individually. Specifically, we pose two key research questions: (1) Do multimodal embeddings as a whole improve recommendation performance? (2) Is each individual modality - text and image - useful when used alone? To isolate the effect of individual modalities - text or visual - we employ a modality knockout strategy by setting the corresponding embeddings to either constant values or random noise. To ensure the scale and comprehensiveness of our study, we evaluate 14 widely used state-of-the-art multimodal recommendation models. Our findings reveal that: (1) multimodal embeddings generally enhance recommendation performance - particularly when integrated through more sophisticated graph-based fusion models. Surprisingly, commonly adopted baseline models with simple fusion schemes, such as VBPR and BM3, show only limited gains. (2) The text modality alone achieves performance comparable to the full multimodal setting in most cases, whereas the image modality alone does not. These results offer foundational insights and practical guidance for the multimodal recommendation community.

cs.IR↗
arXiv2025

Intelligent Prediction and Optimization of Open-Hole Wellbore Multiphysics Stability: A Synergistic PINN-DRL Approach

To address the dual challenge of predicting multiphysics-induced instability and optimizing drilling fluid parameters for open-hole wellbores under long-term exposure, a high-fidelity system of coupled governing equations was developed. This system integrates seepage, hydration-induced softening, thermal diffusion, and elasto-plastic response to capture the nonlinear dynamics of wellbore stability evolution. A two-dimensional numerical model in a polar coordinate system was established using COMSOL Multiphysics to simulate multi-lithology and multi-parameter perturbations. This process generated a high-dimensional dataset characterizing the evolution of Von Mises stress, plastic strain, pore pressure, temperature, and water content, and its physical consistency was examined. Subsequently, the Seepage-Thermal-Water-Mechanical Physics-Informed Neural Network (STWM-PINN) is proposed. This model embeds governing equation residuals and initial-boundary constraints to achieve high-precision, physically consistent predictions of the wellbore's spatio-temporal evolution under the supervision of finite observational data, laying a foundation for parameter control. Building on this, a Double-Noise Soft Actor-Critic (DN-SAC) algorithm is integrated. A reward function was designed to minimize the probability of instability while considering control smoothness and physical boundary constraints, enabling continuous-space optimization of drilling fluid parameters. A case study demonstrates that the proposed method delays the onset of instability by an average of 32.33% and a maximum of 53.35%, significantly reducing instability risk. This study provides a decision-support framework with engineering application potential for intelligent wellbore instability prediction and drilling fluid control.

physics.geo-ph↗
arXiv2025

GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning

Self-supervised learning (SSL) has shown great promise in graph representation learning. However, most existing graph SSL methods are developed and evaluated under a single-dataset setting, leaving their cross-dataset transferability largely unexplored and limiting their ability to leverage knowledge transfer and large-scale pretraining, factors that are critical for developing generalized intelligence beyond fitting training data. To address this gap and advance foundation model research for graphs, we present GSTBench, the first systematic benchmark for evaluating the transferability of graph SSL methods. We conduct large-scale pretraining on ogbn-papers100M and evaluate five representative SSL methods across a diverse set of target graphs. Our standardized experimental setup decouples confounding factors such as model architecture, dataset characteristics, and adaptation protocols, enabling rigorous comparisons focused solely on pretraining objectives. Surprisingly, we observe that most graph SSL methods struggle to generalize, with some performing worse than random initialization. In contrast, GraphMAE, a masked autoencoder approach, consistently improves transfer performance. We analyze the underlying factors that drive these differences and offer insights to guide future research on transferable graph SSL, laying a solid foundation for the "pretrain-then-transfer" paradigm in graph learning. Our code is available at https://github.com/SongYYYY/GSTBench.

cs.LG↗
arXiv2025

TaiBai: A fully programmable brain-inspired processor with topology-aware efficiency

Brain-inspired computing has emerged as a promising paradigm to overcome the energy-efficiency limitations of conventional intelligent systems by emulating the brain's partitioned architecture and event-driven sparse computation. However, existing brain-inspired chips often suffer from rigid network topology constraints and limited neuronal programmability, hindering their adaptability. To address these challenges, we present TaiBai, an event-driven, programmable many-core brain-inspired processor that leverages temporal and spatial spike sparsity to minimize bandwidth and computational overhead. TaiBai chip contains three key features: First, a brain-inspired hierarchical topology encoding scheme is designed to flexibly support arbitrary network architectures while slashing storage overhead for large-scale networks; Second, a multi-granularity instruction set enables programmability of brain-like spiking neuron or synapses with various dynamics and on-chip learning rules; Third, a co-designed compiler stack optimizes task mapping and resource allocation. After evaluating across various tasks, such as speech recognition, ECG classification, and cross-day brain-computer interface decoding, we found spiking neural networks embedded on the TaiBai chip could achieve more than 200 times higher energy efficiency than a standard NVIDIA RTX 3090 GPU at a comparable accuracy. These results demonstrated its high potentiation as a scalable, programmable, and ultra-efficient solution for both multi-scale brain simulation and brain-inspired computation.

cs.AR↗
arXiv2025

One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning

Large-scale models have exhibited remarkable capabilities across diverse domains, including automated medical services and intelligent customer support. However, as most large models are trained on single-modality corpora, enabling them to effectively process and understand multimodal signals remains a significant challenge. Current research often focuses on designing task-specific or scenario-specific tuning strategies, which limits the scalability and versatility. To address this limitation, we propose a unified framework that concurrently handles multiple tasks and modalities. In this framework, all modalities and tasks are represented as unified tokens and trained using a single, consistent approach. To enable efficient multitask processing, we introduce a novel tuning strategy termed neural tuning, inspired by the concept of sparse distributed representation in the human brain, where only specific subsets of neurons are activated for each task. Furthermore, to advance research in multimodal and multitask learning, we present a new benchmark, MMUD, which includes samples annotated with multiple task labels spanning reasoning segmentation, referring segmentation, image captioning, and text-to-image generation. By applying neural tuning to pretrained large models on the MMUD benchmark, we demonstrate the ability to handle multiple tasks simultaneously in a streamlined and efficient manner. All models, code, and datasets will be released publicly upon publication, fostering further research and innovation in this field.

cs.CV↗