arXiv subjects

Junling Wang

Publications and source records attributed to Junling Wang.

At least 19 recordsLinked to original sources

arXiv2026

Unlocking Cryogenic Energy Storage by Constructing Dipole Glass with Unit-cell-level Polar Disorder

Cryogenic energy storage is vital for frontier technologies including deep-space exploration and quantum computing, yet conventional electrochemical energy systems fail below ~230 K due to frozen ion migration. While relaxor-based dielectric capacitors provide high efficiency at room temperature, the intrinsic freezing/growth of polar nanodomains at extended cryogenic regime limits their applications with deteriorated hysteresis losses. Here, we realize superior cryogenic energy-storage performance by designing unit-cell-level disordered dipole-glass state in Pb0.6Sr0.4ZrO3 thin films with composition near antiferroelectric-paraelectric phase boundary. The antiferroelectric-derived dipole-glass introduces enhanced unit-cell-level complexity of dipole interaction that suppresses long-range ferroelectric order. This enables ultralow-hysteresis operation (efficiency > 88%) down to 4 K, delivering record-high energy density (211 J/cm^3) at 9 MV/cm, stability over 10^8 charge/discharge cycles and microsecond-scale charge/discharge capability. This work establishes a dipole-glass paradigm for cryogenic dielectric capacitors, opening a new avenue to highly-efficient energy-storage systems with broad applications in frontier nanoelectronics.

cond-mat.mtrl-sci↗

arXiv2026

Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation

Identifying logical fallacies in everyday discourse is challenging for many people. This challenge is amplified in the era of Large Language Models (LLMs), where malicious agents can deploy fallacious arguments to disseminate misinformation at scale. In this work, we explore the potential of LLMs as part of the solution. We introduce LFTutor, an intelligent tutoring system which uses LLMs to tutor laypeople and help them learn about logical fallacies. LFTutor integrates intent-driven Socratic questioning and critical argumentation principles to actively engage learners to reflect on their reasoning. Through both automatic and human evaluations, we demonstrate that LFTutor significantly outperforms baseline LLMs lacking these pedagogical strategies. This work highlights the promise of combining LLMs with pedagogical scaffolding to foster critical thinking and argument literacy in the age of AI.

cs.AI↗

arXiv2026

Logit Distillation on Manifolds: Mapping by Learning

A simple way to improve the performance of almost any machine learning model is not to train a single but several models with diverse algorithms which will make slightly distinct kinds of predictions and errors on the same data, and thus improve the average predictions and robustness. However, making predictions using a whole ensemble of models is cumbersome and computationally too expensive to allow deployment to a large number of users, especially if the models are large neural nets. In response to this, we introduce a layer and point wise projection mapping, which maps student and teacher representations into an aligned high-dimensional embedding space during training process. The proposed approach combined with LoRA injection reduces the student model trainable parameters to less than 1% of the teacher model, while significantly improving word error rate (WER) compared to other distillation methods, as demonstrated in ablation studies. Unlike a mixture of experts, our method can be trained rapidly and in parallel.

cs.LG↗

arXiv2026

Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education

AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models.

cs.CV↗

arXiv2026

Unveiling the Visual Counting Bottleneck in Vision-Language Models

While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting. In this work, we investigate this extrapolation bottleneck by deconstructing visual counting into three cognitive stages: visual individuation, magnitude awareness, and symbolic mapping. Using synthetic Go boards and linear probes, we demonstrate that visual backbones maintain robust, linearly separable representations of quantity well into the extrapolation regime, ruling out perceptual failure. Furthermore, models retain latent magnitude awareness, successfully performing comparative reasoning on quantities they fail to enumerate. We pinpoint the collapse to the symbolic mapping stage, where the model fails to project valid visual magnitudes onto symbolic tokens. Our findings support a frac tured magnitude hypothesis: VLMs fail to acquire a universal number space, instead learning disjoint, modality-specific statistical manifolds that prevent cross-modal grounding for unseen quantities. Validated on the state-of-the-art foundation model, our results suggest that bridging this gap requires inductive priors enforcing unified representations, as data scaling alone is insufficient.

cs.MM↗

arXiv2026

When Should Teachers Control AI Generation for Mathematics Visuals?

Generative AI has the potential to help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be pedagogically meaningful and instructionally correct. However, current generative tools primarily support prompting and post-hoc editing, leaving open a key question for correctness-sensitive educational authoring: when in the generation pipeline should teachers exert control? In this paper, we investigate how the timing of human control in AI-assisted generation shapes teachers' visual authoring practices in correctness-sensitive tasks. We introduce a design space of three stages of control: pre-generation control, where users specify intent solely through natural language prompts before generation; mid-generation control, where users inspect and confirm an explicit layout structure before the system completes generation; and post-generation control, where users directly modify AI-generated visuals after generation through object-level edits. In a within-subject, mixed-methods study with 24 primary mathematics teachers, post-generation control received higher ratings on predictability and correctness, while other subjective measures showed no reliable differences. Qualitative findings explain these differences by revealing workflow trade-offs: highly automated, pre-generation control supports rapid ideation but reduces perceived agency and predictability; mid-generation control improves structural alignment at the cost of additional effort; and post-generation control preserves user agency through low-cost, direct verification and correction. Together, these results suggest that in correctness-sensitive educational tasks, effective generative tools should align system behavior with teacher intent and support stage-dependent workflows that combine automation with direct manipulation.

cs.HC↗

arXiv2026

GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

Several educational domains rely heavily on diagrams and visual cues, yet most existing tutoring datasets are limited to text-only interactions. This limits the development of AI tutors that can teach in visually grounded ways used by human instructors. Thus, we introduce GeoDial, a multimodal tutoring dataset of over 1.3K teacher-student dialogs in the domain of geometry collected from experienced math teachers, where instructional turns are explicitly grounded in diagram highlights. We propose a scalable annotation protocol that integrates dialog acts, visual highlighting, and feedback, enabling fine-grained supervision of both language and visual tutoring behavior. To illustrate the challenges posed by this setting, we fine-tune several vision-language models on GeoDial and evaluate their ability to generate tutoring utterances and diagram highlights. While supervised fine-tuning substantially improves the quality of generated dialog, it struggles to produce accurate diagram highlights, revealing a key limitation of current methods and highlighting the need for approaches that more effectively integrate visual reasoning with pedagogical interaction.

cs.CY↗

arXiv2026

Two-Point Resolution in Spectral Super-Resolution

Two-point super-resolution is an important problem in many signal processing applications. In this paper, we aim to establish a resolution theory for two-point super-resolution from a single snapshot. We consider a complex two-point model with unequal amplitudes and a nontrivial relative phase, and derive super-resolution upper bounds (SRUs) guaranteeing resolvability as well as super-resolution lower bounds (SRLs) below which stable reconstruction is impossible. The resulting bounds provide an explicit characterization of how the amplitude ratio and, more importantly, the relative phase affect the resolution limit for both source-number detection and location estimation. In the in-phase regime, the classical resolution exponents are retained: $(\sigma/m)^{1/2}$ for source-number detection and $(\sigma/m)^{1/3}$ for location estimation. In the out-of-phase regimes, the phase term significantly changes the resolution limit: it acts as a direct subtractive term in the near-endpoint regime, and improves the scaling orders in the large-phase regime to $\sigma/m$ for source-number detection and $(\sigma/m)^{1/2}$ for location estimation. Extensive numerical experiments across different phase regimes and reconstruction algorithms validate the predicted scaling laws and theoretical resolution boundaries. Moreover, comparison with our resolution limit in all phase regimes reveals the optimality of $\ell_0$, ML, and ESPRIT algorithms, and the non-optimality of SVT, MUSIC, and the convex method, a finding that, to the best of our knowledge, has not been reported before. Collectively, our results show that the phase of amplitudes is not merely a nuisance in super-resolution, but a key factor that can be exploited to improve stable resolvability.

eess.SP↗

arXiv2026

MetaBlue: A Metasurface-Assisted Acoustic Underwater Localization System

Underwater localization is essential for marine exploration and autonomous underwater operations, yet existing radio frequency and optical approaches are limited by rapid attenuation or limited visibility. Acoustic sensing remains the most practical choice, but conventional acoustic systems typically rely on large arrays or multiple synchronized anchors, resulting in high hardware costs and complex deployment. This paper introduces a novel low-cost passive acoustic metasurface, MetaBlue , explicitly designed for underwater localization, which, when attached to an ordinary ultrasonic transmitter, transforms it into a directional "super-transmitter." The metasurface embeds direction-dependent spectral patterns into the transmitted waveform, enabling accurate angle-of-arrival (AoA) estimation using only a single hydrophone. For ranging, we present a new EM-acoustic mixed time-of-arrival (ToA) method that leverages the acoustic transducer's inherent low-frequency EM leakage as a timing reference, enabling precise ranging without shared clocks. This allows complete 3D localization with a single low-cost anchor. We evaluate the system across diverse real-world underwater settings, including pools, tanks, and outdoor environments. Experiments show that our design achieves an average AoA error of 8.7 degree and 3D localization error of 0.37 m at distances over 10 m. Even with a single anchor, the system maintains 0.73 m precision.

cs.NI↗

arXiv2026

SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

Despite recent successes, test-time scaling -- i.e., dynamically expanding the token budget during inference as needed -- remains brittle for vision-language models (VLMs). Unstructured visual reasoning chains entangle perception and reasoning, leading to long, disorganized contexts where small perceptual mistakes may cascade into completely wrong answers. Reasoning also requires expensive reinforcement learning with hand-crafted rewards. Here, we introduce SPARC (Separating Perception And Reasoning Circuits), a modular framework that explicitly decouples visual perception from reasoning. Inspired by sequential sensory-to-cognitive processing in the brain, SPARC implements a two-stage pipeline where the model first performs explicit visual search to localize question-relevant regions, then conditions its reasoning on those regions to produce the final answer. This separation enables independent test-time scaling with asymmetric compute allocation (e.g., prioritizing perceptual processing under distribution shift), and supports selective optimization (e.g., improving the perceptual stage alone when it is the bottleneck for end-to-end performance). It also accommodates compressed contexts by running global search at lower image resolutions and allocating high-resolution processing only to selected regions, thereby reducing visual token count and compute. SPARC outperforms monolithic baselines and strong visual-grounding approaches across challenging visual reasoning tasks, such as improving Qwen3VL 4B on the $V^*$ VQA benchmark by 6.7 points and surpassing "thinking with images" by 4.6 points in an OOD setting with a $200\times$ lower token budget.

cs.CV↗

arXiv2026

UI Remix: Supporting UI Design Through Interactive Example Retrieval and Remixing

Designing user interfaces (UIs) is a critical step when launching products, building portfolios, or personalizing projects, yet end users without design expertise often struggle to articulate their intent and to trust design choices. Existing example-based tools either promote broad exploration, which can cause overwhelm and design drift, or require adapting a single example, risking design fixation. We present UI Remix, an interactive system that supports mobile UI design through an example-driven design workflow. Powered by a multimodal retrieval-augmented generation (MMRAG) model, UI Remix enables iterative search, selection, and adaptation of examples at both the global (whole interface) and local (component) level. To foster trust, it presents source transparency cues such as ratings, download counts, and developer information. In an empirical study with 24 end users, UI Remix significantly improved participants' ability to achieve their design goals, facilitated effective iteration, and encouraged exploration of alternative designs. Participants also reported that source transparency cues enhanced their confidence in adapting examples. Our findings suggest new directions for AI-assisted, example-driven systems that empower end users to design with greater control, trust, and openness to exploration.

cs.HC↗

arXiv2026

Bridging Instead of Replacing Online Coding Communities with AI through Community-Enriched Chatbot Designs

LLM-based chatbots like ChatGPT have become popular tools for assisting with coding tasks. However, they often produce isolated responses and lack mechanisms for social learning or contextual grounding. In contrast, online coding communities like Kaggle offer socially mediated learning environments that foster critical thinking, engagement, and a sense of belonging. Yet, growing reliance on LLMs risks diminishing participation in these communities and weakening their collaborative value. To address this, we propose Community-Enriched AI, a design paradigm that embeds social learning dynamics into LLM-based chatbots by surfacing user-generated content and social design feature from online coding communities. Using this paradigm, we implemented a RAG-based AI chatbot leveraging resources from Kaggle to validate our design. Across two empirical studies involving 28 and 12 data science learners, respectively, we found that Community-Enriched AI significantly enhances user trust, encourages engagement with community, and effectively supports learners in solving data science tasks. We conclude by discussing design implications for AI assistance systems that bridge -- rather than replace -- online coding communities.

cs.HC↗

arXiv2025

Can Vision-Language Models Solve Visual Math Equations?

Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images, variables are represented by object icons, and coefficients must be inferred by counting. While VLMs perform well on textual equations, they fail on visually grounded counterparts. To understand this gap, we decompose the task into coefficient counting and variable recognition, and find that counting is the primary bottleneck, even when recognition is accurate. We also observe that composing recognition and reasoning introduces additional errors, highlighting challenges in multi-step visual reasoning. Finally, as equation complexity increases, symbolic reasoning itself becomes a limiting factor. These findings reveal key weaknesses in current VLMs and point toward future improvements in visually grounded mathematical reasoning.

cs.CL↗

arXiv2025

Electric Field Control of Spin Orbit Coupling and Circular Photogalvanic Effect in a True Ferrielectric Crystal

Materials possessing long range ordering of magnetic spins or electric dipoles have been the focus of condensed matter research. Among them, ferri-systems with two sublattices of unequal/noncollinear spins or electric dipoles are expected to combine the properties of ferro- and antiferro-systems, but lack experimental observations in single phase materials. This is particularly true for the ferrielectric system, since the electric dipoles usually can be redefined to incorporate the two sublattices into one, making it indistinguishable from ferroelectric. This raises doubts about whether or not ferrielectricity can be considered as an independent ferroic order. Here we report the observation of true ferrielectric behaviors in a hybrid single crystal (MV)[SbBr5] (MV2+ = N,N'-dimethyl-4,4'-bipyridinium or methylviologen), where the two electric dipole sublattices switch asynchronously, thus cannot be reduced to ferroelectric by redefining the unit cell. Furthermore, the complex dipole configuration imparts circularly polarized light sensitivity to the system. An electric field can modulate the non-collinear dipole sublattices and even induce a transition from ferrielectric to ferroelectric state, thereby tuning the helicity-dependent photocurrent. This study opens a new paradigm for the study of true irreducible ferrielectricity (a new class of polar system) and provides an effective approach to the electric field control of spin-orbit coupling and circular photogalvanic effect.

cond-mat.mtrl-sci↗

arXiv2025

Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models

Visuals are valuable tools for teaching math word problems (MWPs), helping young learners interpret textual descriptions into mathematical expressions before solving them. However, creating such visuals is labor-intensive and there is a lack of automated methods to support this process. In this paper, we present Math2Visual, an automatic framework for generating pedagogically meaningful visuals from MWP text descriptions. Math2Visual leverages a pre-defined visual language and a design space grounded in interviews with math teachers, to illustrate the core mathematical relationships in MWPs. Using Math2Visual, we construct an annotated dataset of 1,903 visuals and evaluate Text-to-Image (TTI) models for their ability to generate visuals that align with our design. We further fine-tune several TTI models with our dataset, demonstrating improvements in educational visual generation. Our work establishes a new benchmark for automated generation of pedagogically meaningful visuals and offers insights into key challenges in producing multimodal educational content, such as the misrepresentation of mathematical relationships and the omission of essential visual elements.

cs.CL↗

arXiv2025

DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition

Decomposition is a fundamental skill in algorithmic programming, requiring learners to break down complex problems into smaller, manageable parts. However, current self-study methods, such as browsing reference solutions or using LLM assistants, often provide excessive or generic assistance that misaligns with learners' decomposition strategies, hindering independent problem-solving and critical thinking. To address this, we introduce Decomposition Box (DBox), an interactive LLM-based system that scaffolds and adapts to learners' personalized construction of a step tree through a "learner-LLM co-decomposition" approach, providing tailored support at an appropriate level. A within-subjects study (N=24) found that compared to the baseline, DBox significantly improved learning gains, cognitive engagement, and critical thinking. Learners also reported a stronger sense of achievement and found the assistance appropriate and helpful for learning. Additionally, we examined DBox's impact on cognitive load, identified usage patterns, and analyzed learners' strategies for managing system errors. We conclude with design implications for future AI-powered tools to better support algorithmic programming education.

cs.HC↗

arXiv2024

Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots

Educational chatbots are a promising tool for assisting student learning. However, the development of effective chatbots in education has been challenging, as high-quality data is seldom available in this domain. In this paper, we propose a framework for generating synthetic teacher-student interactions grounded in a set of textbooks. Our approaches capture one aspect of learning interactions where curious students with partial knowledge interactively ask a teacher questions about the material in the textbook. We highlight various quality criteria that such dialogues should fulfill and compare several approaches relying on either prompting or fine-tuning large language models. We use synthetic dialogues to train educational chatbots and show benefits of further fine-tuning in different educational domains. However, human evaluation shows that our best data synthesis method still suffers from hallucinations and tends to reiterate information from previous conversations. Our findings offer insights for future efforts in synthesizing conversational data that strikes a balance between size and quality. We will open-source our data and code.

cs.CL↗

arXiv2022

Ferroelectricity going 2D

The discoveries of magnetism and ferroelectricity in 2D van der Waals (vdW) materials have brought important functionalities to the 2D materials family, and may trigger a revolution in next generation nanoelectronics and spintronics. In this perspective article, we briefly review the recent progress in the field of 2D ferroelectrics, focusing on the mechanisms that drive spontaneous polarizations in 2D systems, unique properties brought about by the reduced lattice dimensionality, and promising applications of 2D ferroelectrics. At the end, we provide an outlook for challenges that need to be addressed and our view on possible future research directions.

cond-mat.mtrl-sci↗