arXiv subjects

Zheng Sun

Publications and source records attributed to Zheng Sun.

At least 37 records · Page 2Linked to original sources

arXiv2026

Scaling Two-Dimensional Semiconductor Nanoribbons for High-Performance Electronics

As silicon transistors scale toward future technology nodes, three-dimensional architectures -- including gate-all-around (GAA) nanoribbon and complementary field-effect transistors (CFETs) -- require channel widths in the tens of nanometers to meet density targets. Monolayer transition metal dichalcogenides (TMDs), with their atomically thin bodies, are promising channel materials for these architectures, yet most TMD-based FETs remain limited to micrometer-scale widths. Here, we show that channel width scaling of monolayer MoS2 nanoribbon transistors not only preserves but also enhances device performance. Reducing the channel width from hundreds of nanometers to $\sim$30--40 nm increases the median on-current density by $\sim$42% and reduces the median subthreshold swing by $\sim$16%, with a champion device reaching 995 $μ$A $μ$m$^{-1}$ at a drain-to-source voltage of 1 V and an overdrive voltage of 2.5 V. We attribute these improvements to three mechanisms: minimal edge-induced disorder, enhanced gate electrostatics at ribbon edges, and more efficient side-contact injection, together reducing contact resistance from $\sim$860 $Ω$ $μ$m to $\sim$270 $Ω$ $μ$m. Extending the platform to n-type WS2 and p-type WSe2 FETs, we achieve WSe2 p-FET on-currents of 357 $μ$A $μ$m$^{-1}$. These findings suggest that monolayer TMD nanoribbon FETs are promising candidates for future ultra-scaled electronics.

cond-mat.mtrl-sci↗

arXiv2026

Thinking with Drafting: Optical Decompression via Logical Reconstruction

Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems transcribe symbols without capturing logical topology, while pixel-based generative models produce visual artifacts lacking mathematical exactness. To bridge this gap, we propose that reasoning over visual inputs be reconceptualized as optical decompression-the process of reconstructing latent logical structures from compressed visual tokens. Guided by the axiom that Parsing is Reasoning, we introduce Thinking with Drafting (TwD), which utilizes a minimalist Domain-Specific Language (DSL) as a grounding intermediate representation. Unlike standard approaches that hallucinate answers directly, TwD forces the model to draft its mental model into executable code, rendering deterministic visual proofs for self-verification. To validate this, we present VisAlg, a visual algebra benchmark. Experiments demonstrate that TwD serve as a superior cognitive scaffold. Our work establishes a closed-loop system where visual generation acts not as a creative output but as a logical verifier, offering a generalizable path for visual reasoning.

cs.CL↗

arXiv2026

How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning

Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities in visual generation and plotting, we identify a counter-intuitive and underexplored phenomenon. Naively applying Supervised Fine-Tuning (SFT) on interleaved plot-solution data leads to a substantial degradation in reasoning performance compared to text-only baselines. We argue that this failure stems from a fundamental limitation of SFT, which primarily induces distributional alignment: the model learns to reproduce the surface format of interleaved plotting but fails to internalize the causal dependency between the generated plot and reasoning steps. To overcome this limitation, we propose Faire (Functional alignment for interleaved reasoning), a reinforcement learning framework that enforces three casual constraints to move beyond superficial imitation toward functional alignment. Extensive experiments show that Faire induces a qualitative shift in model behavior in which the plotting is effectively internalized, yielding competitive performance on challenging geometric reasoning benchmarks.

cs.CL↗

arXiv2026

Solar Energetic Particle Events and Associated Type II Radio Bursts from Different Source Regions

Large solar energetic particle (SEP) events are thought to originate from the shocks driven by fast coronal mass ejections (CMEs) and thus generally accompanied by type II radio bursts. However, a significant proportion of type II radio bursts is not accompanied by SEP events. To study the relationship between SEPs and type II radio bursts and the associated physical mechanisms, we statistically analyze 43 SEP halo-CMEs and 131 non-SEP halo-CMEs observed from 2010 to 2024, and check the related properties of type II radio bursts and solar source region. We find nearly all SEP events and approximately two-thirds of non-SEP events are accompanied by type II radio bursts. Type II radio bursts associated with SEP events usually have longer duration and lower ending frequencies. The starting frequency exhibits a clear source region dependence, being highest for ''single active region (AR)'', intermediate for ''multiple ARs'', and lowest for ''outside of ARs''. Furthermore, the spectra of both protons and electrons exhibit a similar softening trend in the three types of source regions. Joint analysis of spectra and type II radio bursts reveals that the proton spectra index has a good anti-correlation with the starting frequency of the type II radio bursts. Our statistical results have important implications for the mechanisms behind SEP acceleration

astro-ph.SR↗

arXiv2026

GEditBench v2: A Human-Aligned Benchmark for General Image Editing

Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics fail to adequately capture visual consistency, i.e., the preservation of identity, structure and semantic coherence between edited and original images. To address these limitations, we introduce GEditBench v2, a comprehensive benchmark with 1,200 real-world user queries spanning 23 tasks, including a dedicated open-set category for unconstrained, out-of-distribution editing instructions beyond predefined tasks. Furthermore, we propose PVC-Judge, an open-source pairwise assessment model for visual consistency, trained via two novel region-decoupled preference data synthesis pipelines. Besides, we construct VCReward-Bench using expert-annotated preference pairs to assess the alignment of PVC-Judge with human judgments on visual consistency evaluation. Experiments show that our PVC-Judge achieves state-of-the-art evaluation performance among open-source models and even surpasses GPT-5.1 on average. Finally, by benchmarking 16 frontier editing models, we show that GEditBench v2 enables more human-aligned evaluation, revealing critical limitations of current models, and providing a reliable foundation for advancing precise image editing.

cs.CV↗

arXiv2026

A limiter-based approach to construct high-order fully-discrete entropy stable explicit DG schemes for hyperbolic conservation laws

This paper presents a class of novel high-order fully-discrete entropy stable (ES) discontinuous Galerkin (DG) schemes with explicit time discretization. The proposed methodology exploits a critical observation from [4] that the cell averages of classical DG solutions with forward Euler time stepping satisfy an ``entropy-stable-like'' property. Building on this result, fully-discrete entropy stability is rigorously enforced through a simple Zhang--Shu-type scaling limiter [45] applied as a post-processing step, without modifying the underlying spatial discretization. Furthermore, the proposed methodology can simultaneously enforce multiple cell entropy inequalities, a capability unavailable in existing ES DG schemes. High-order accuracy in time is achieved by using strong-stability-preserving (SSP) multistep methods. Theoretically, we prove that the proposed scheme indeed maintains high-order accuracy and establish a Lax--Wendroff-type theorem guaranteeing that the limit of the numerical solutions, if it exists, satisfies the desired entropy inequality. Extensive numerical tests for scalar equations and systems, including the nonconvex Buckley--Leverett problem and extreme examples of Euler equations, demonstrate optimal accuracy, enforcement of multiple entropy conditions, and strong robustness.

math.NA↗

arXiv2026

SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language Models

The performance of image generation has been significantly improved in recent years. However, the study of image screening is rare, and its performance with Multimodal Large Language Models (MLLMs) is unsatisfactory due to the lack of data and the weak spatial plausibility reasoning ability in MLLMs. In this work, we propose a complete solution to address these problems in terms of data and methodology. For data, we collect a comprehensive spatial plausibility reasoning (SPR) dataset with over 128k samples, called SPR-128K. The dataset evaluates spatial plausibility reasoning ability under four aspects. Regarding data annotation, we investigate multiple approaches to acquire high-quality Chain-of-Thought (CoT) data in the most cost-effective manner. Methodologically, we introduce a Dynamic Proportional Accuracy (DPA) reward into the Group Relative Policy Optimization (GRPO) framework, called DPA-GRPO. This enhanced method demonstrates superior performance compared to the original GRPO. Our experiments reveal that even leading MLLMs exhibit unsatisfactory performance in spatial plausibility reasoning. In contrast, our much smaller model, leveraging DPA-GRPO, substantially surpasses both large open-source and leading closed-source models.

cs.CV↗

arXiv2026

Physical remnant of electroweak theta angles

In addition to the well-known quantum chromodynamical theta angle, we show that the Standard Model has another theta angle which is invariant under arbitrary chiral rotations of quarks and leptons. The new theta angle can be identified with the quantum electrodynamical theta angle, which should be viewed as an independent parameter of the Standard Model, and may be observable in spacetime with non-simply connected features, either beyond the visible universe or in an effective background from a laboratory setup.

hep-ph↗

arXiv2026

PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents

Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learning models. However, research in this area is often hindered by the scarcity of diverse and accessible data. To address this limitation, we propose a novel method for synthesizing realistic digital footprints using large language model (LLM) agents. Starting from a structured user profile, our approach generates diverse and plausible sequences of user events, ultimately producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc. Intrinsic evaluation results demonstrate that the generated dataset is more diverse and realistic than existing baselines. Moreover, models fine-tuned on our synthetic data outperform those trained on other synthetic datasets when evaluated on real-world out-of-distribution tasks.

cs.CL↗

arXiv2026

Fine Structure and Formation Mechanism of a Sunspot Bipolar Light Bridge in NOAA AR 13663

Bipolar Light Bridges (BLBs) are bright regions located between sunspot umbrae of opposite magnetic polarity. They are typically characterized by strong magnetic fields and intense flows, which are believed to be closely associated with major solar flares. Despite their importance, their fine structure, formation and evolution remain poorly understood. In this work, we analyze the observations of a well-defined BLB obtained by the Goode Solar Telescope at the Big Bear Solar Observatory and the Helioseismic and Magnetic Imager onboard the Solar Dynamics Observatory. The high-resolution GST observations reveal that the BLB is composed of fine, penumbral filament-like structures with widths of approximately 100-150 km. The corresponding Doppler velocity maps present a stable pattern of spatially adjacent red- and blueshifted patches within the BLB throughout the 5.5-hour GST observation. HMI observations show that the BLB arises from the converging and shearing motions of sunspots with opposite polarities. Penumbral regions originating from different polarities gradually evolve and interact, eventually forming the BLB. The observed Doppler velocity pattern, characterized by red- and blueshifted patches, can be interpreted as a projection effect of the Evershed flow within the penumbrae. Therefore, we argue that the BLB is formed through the compression and stretching of penumbral structures from oppositely polarized sunspots.

astro-ph.SR↗

arXiv2026

The Trinity of Consistency as a Defining Principle for General World Models

The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial General Intelligence. Recent advancements represented by video generation models like Sora have demonstrated the potential of data-driven scaling laws to approximate physical dynamics, while the emerging Unified Multimodal Model (UMM) offers a promising architectural paradigm for integrating perception, language, and reasoning. Despite these advances, the field still lacks a principled theoretical framework that defines the essential properties requisite for a General World Model. In this paper, we propose that a World Model must be grounded in the Trinity of Consistency: Modal Consistency as the semantic interface, Spatial Consistency as the geometric basis, and Temporal Consistency as the causal engine. Through this tripartite lens, we systematically review the evolution of multimodal learning, revealing a trajectory from loosely coupled specialized modules toward unified architectures that enable the synergistic emergence of internal world simulators. To complement this conceptual framework, we introduce CoW-Bench, a benchmark centered on multi-frame reasoning and generation scenarios. CoW-Bench evaluates both video generation models and UMMs under a unified evaluation protocol. Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.

cs.AI↗

arXiv2026

Canvas-of-Thought: Grounding Reasoning via Mutable Structured States

While Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), relying solely on linear text sequences remains a bottleneck for complex tasks. We observe that even when auxiliary visual elements are interleaved, they are often treated as static snapshots within a one-dimensional, unstructured reasoning chain. We argue that such approaches treat reasoning history as an immutable stream: correcting a local error necessitates either generating verbose downstream corrections or regenerating the entire context. This forces the model to implicitly maintain and track state updates, significantly increasing token consumption and cognitive load. This limitation is particularly acute in high-dimensional domains, such as geometry and SVG design, where the textual expression of CoT lacks explicit visual guidance, further constraining the model's reasoning precision. To bridge this gap, we introduce \textbf{Canvas-of-Thought (Canvas-CoT)}. By leveraging a HTML Canvas as an external reasoning substrate, Canvas-CoT empowers the model to perform atomic, DOM-based CRUD operations. This architecture enables in-place state revisions without disrupting the surrounding context, allowing the model to explicitly maintain the "ground truth". Furthermore, we integrate a rendering-based critique loop that serves as a hard constraint validator, providing explicit visual feedback to resolve complex tasks that are difficult to articulate through text alone. Extensive experiments on VCode, RBench-V, and MathVista demonstrate that Canvas-CoT significantly outperforms existing baselines, establishing a new paradigm for context-efficient multimodal reasoning.

cs.CL↗

arXiv2026

Anomalous valley Hall dynamics of exciton-polaritons

The valley degree of freedom in atomically thin transition-metal dichalcogenides provides a natural binary index for information processing. Exciton-polaritons formed under strong light-matter coupling offer a promising route to overcome the limited lifetime and transport of bare valley excitons. Here we report an anomalous optical valley Hall effect in a monolayer WS2 exciton-polariton system. Using polarization- and time-resolved real-space imaging, we directly visualize a symmetry-breaking spatial separation of polaritons from opposite valleys under linearly polarized excitation, accompanied by an ultrafast Hall drift velocity on the order of 10^5 m/s. This behaviour cannot be accounted for by conventional cavity-induced mechanisms and instead points to a strain-induced synthetic pseudomagnetic field acting on the excitonic component of polaritons. Our results establish exciton-polaritons as a high-speed and optically accessible platform for valley transport, opening pathways towards tunable valleytronic and topological photonic devices.

cond-mat.mes-hall↗

arXiv2025

DCAF-Net: Dual-Channel Attentive Fusion Network for Lower Limb Motion Intention Prediction in Stroke Rehabilitation Exoskeletons

Rehabilitation exoskeletons have shown promising results in promoting recovery for stroke patients. Accurately and timely identifying the motion intentions of patients is a critical challenge in enhancing active participation during lower limb exoskeleton-assisted rehabilitation training. This paper proposes a Dual-Channel Attentive Fusion Network (DCAF-Net) that synergistically integrates pre-movement surface electromyography (sEMG) and inertial measurement unit (IMU) data for lower limb intention prediction in stroke patients. First, a dual-channel adaptive channel attention module is designed to extract discriminative features from 48 time-domain and frequency-domain features derived from bilateral gastrocnemius sEMG signals. Second, an IMU encoder combining convolutional neural network (CNN) and attention-based long short-term memory (attention-LSTM) layers is designed to decode temporal-spatial movement patterns. Third, the sEMG and IMU features are fused through concatenation to enable accurate recognition of motion intention. Extensive experiment on 11 participants (8 stroke subjects and 3 healthy subjects) demonstrate the effectiveness of DCAF-Net. It achieved a prediction accuracies of 97.19% for patients and 93.56% for healthy subjects. This study provides a viable solution for implementing intention-driven human-in-the-loop assistance control in clinical rehabilitation robotics.

q-bio.QM↗

arXiv2025

Resolving Interchange Reconnection Dynamics in a Fan-Spine-like Topology Observed by Solar Orbiter

Interchange reconnection is believed to play a significant role in the production of solar jets and solar wind. However, the dynamics of interchange reconnection in the low corona might be more complex than recognized before in higher temporal and spatial resolutions. Using unprecedentedly high-resolution observations from the Extreme Ultraviolet Imager (EUI) onboard the Solar Orbiter, we analyze the dynamics of interchange reconnection in a small-scale fan-spine-like topology. Interchange reconnection that continuously occurs around the multi-null points of the fan-spine-like system exhibits a quasi-periodicity of ~200 s, nearly covering the entire evolution of this system. Continuous evolution and reversal of multiple current sheets are observed over time near the null point. These results reveal that the dynamics of interchange reconnection are likely modulated by the emerging magnetic structures, such as mini-filaments and emerging arcades. Moreover, a curtain-like feature with a width of 1.7 Mm is also observed near the interchange reconnection region and persistently generates outflows, which is similar to the separatrix curtain reported in the pseudo-streamer structure. This study not only demonstrates the complex and variable reconnection dynamics of interchange reconnection within small-scale fan-spine topology but also provides insights into the self-similarity of magnetic field configurations across multiple temporal and spatial scales.

astro-ph.SR↗

arXiv2025

Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning

Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimodal data, especially challenging in specialized domains like chemistry, earth sciences, and multimodal mathematics. Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties, ultimately causing reward hacking: models exploit high-reward patterns, collapsing policy entropy and destabilizing training. We propose DoGe (Decouple to Generalize), a dual-decoupling framework that guides models to first learn from context rather than problem solving by refocusing on the problem context scenarios overlooked by synthetic data methods. By decoupling learning process into dual components (Thinker and Solver), we reasonably quantify the reward signals of this process and propose a two-stage RL post-training approach from freely exploring context to practically solving tasks. Second, to increase the diversity of training data, DoGe constructs an evolving curriculum learning pipeline: an expanded native domain knowledge corpus and an iteratively evolving seed problems pool. Experiments show that our method consistently outperforms the baseline across various benchmarks, providing a scalable pathway for realizing self-evolving LVLMs.

cs.AI↗

arXiv2025

A Hyperspectral Imaging Guided Robotic Grasping System

Hyperspectral imaging is an advanced technique for precisely identifying and analyzing materials or objects. However, its integration with robotic grasping systems has so far been explored due to the deployment complexities and prohibitive costs. Within this paper, we introduce a novel hyperspectral imaging-guided robotic grasping system. The system consists of PRISM (Polyhedral Reflective Imaging Scanning Mechanism) and the SpectralGrasp framework. PRISM is designed to enable high-precision, distortion-free hyperspectral imaging while simplifying system integration and costs. SpectralGrasp generates robotic grasping strategies by effectively leveraging both the spatial and spectral information from hyperspectral images. The proposed system demonstrates substantial improvements in both textile recognition compared to human performance and sorting success rate compared to RGB-based methods. Additionally, a series of comparative experiments further validates the effectiveness of our system. The study highlights the potential benefits of integrating hyperspectral imaging with robotic grasping systems, showcasing enhanced recognition and grasping capabilities in complex and dynamic environments. The project is available at: https://zainzh.github.io/PRISM.

cs.RO↗

arXiv2025

From fractional Chern insulators to topological electronic crystals in moiré MoTe2: quantum geometry tuning via remote layer

The quantum geometry of Bloch wavefunctions,encoded in the Berry curvature and quantum metric, is believed to be a decisive ingredient in stabilizing fractional quantum anomalous Hall (FQAH) effect(i.e., fractional Chern insulator, FCI, at zero magnetic field), against competing symmetry-breaking phases.A direct experimental demonstration of quantum geometry-driven switching between distinct correlated topological phases, however, has been lacking. Here, we report experimental evidence of such a switch in a high-quality 3.7 twisted MoTe2 (tMoTe2) device consisting of both A-A bilayer and A-AB trilayer regions. While composite Fermi liquid CFL/FQAH phases are established in A-A tMoTe2,the A-AB region-effectively an A-A moire bilayer proximitized by a remote B layer-develops a series of topological electronic crystal (TEC, also referred to as generalized QAH crystal, QAHC) states with integer quantized Hall conductance at commensurate fractional fillings v=1/2, 2/3, and an incommensurate filling factor v=0.53.The electrostatic phase diagram is mapped out by combined transport and optical measurements, showing that these TEC states emerge within the first moir'e valence band prior to any charge transfer to the B layer. Exact diagonalization (ED) incorporating the remote-layer-induced intralayer potential demonstrates a transition from a CFL-like manifold in the A-A limit to a Chern number C=1 ground-state consistent with a TEC at v=1/2 , accompanied by the further breakdown of ideal band geometry. Our results provide experimental evidence of quantum geometry-tuned competition between FQAH/CFL and TEC phases in a moiré Chern band and pave the way for further exploring correlation-driven topological phenomena by tuning quantum geometry.

cond-mat.mes-hall↗