arXiv subjects

Yuyang Li

Publications and source records attributed to Yuyang Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Advances and Challenges in Solar Flare Prediction: A Review

Solar flares, as one of the most prominent manifestations of solar activity, have a profound impact on both the Earth's space environment and human activities. As a result, accurate solar flare prediction has emerged as a central topic in space weather research. In recent years, substantial progress has been made in the field of solar flare forecasting, driven by the rapid advancements in space observation technology and the continuous improvement of data processing capabilities. This paper presents a comprehensive review of the current state of research in this area, with a particular focus on tracing the evolution of data-driven approaches -- which have progressed from early statistical learning techniques to more sophisticated machine learning and deep learning paradigms, and most recently, to the emergence of Multimodal Large Models (MLMs). Furthermore, this study examines the realistic performance of existing flare forecasting platforms, elucidating their limitations in operational space weather applications and thereby offering a practical reference for future advancements in technological optimization and system design.

astro-ph.SR↗

arXiv2026

In-Orbit GRB Identification Using LLM-based model for the CXPD CubeSat

To validate key technologies for wide field-of-view (FOV) X-ray polarization measurements, the Cosmic X-ray Polarization Detector (CXPD) CubeSat series has been developed as a prototype platform for the Low-Energy X-ray Polarization Detector (LPD) onboard the POLAR-2 mission. The wide-FOV design significantly increases the complexity of the background environment, posing notable challenges for real-time gamma-ray burst (GRB) identification. In this work, we propose an in-orbit GRB identification method based on machine learning, using simulated spectral data as input. A training dataset was constructed using a Geant4-based simulator, incorporating in-orbit background and GRB events modeled within the 2-10 keV energy range. To meet the computational constraints of onboard processing, we employ a multimodal large language model (MLLM), which is fine-tuned using low-rank adaptation (LoRA) based on miniCPM-V2.6 and quantized to 4-bit precision. The model achieves perfect classification accuracy on validation data and demonstrates strong regression performance in estimating GRB spectral indices, with an RMSE of 0.118. Furthermore, we validate the feasibility of onboard deployment through a simulated satellite data processing pipeline, highlighting the potential of our approach to enable future real-time GRB detection and spectral analysis in orbit.

astro-ph.IM↗

arXiv2026

Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation

Robotic manipulation requires both rich multimodal perception and effective learning frameworks to handle complex real-world tasks. See-through-skin (STS) sensors, which combine tactile and visual perception, offer promising sensing capabilities, while modern imitation learning provides powerful tools for policy acquisition. However, existing STS designs lack simultaneous multimodal perception and suffer from unreliable tactile tracking. Furthermore, integrating these rich multimodal signals into learning-based manipulation pipelines remains an open challenge. We introduce TacThru, an STS sensor enabling simultaneous visual perception and robust tactile signal extraction, and TacThru-UMI, an imitation learning framework that leverages these multimodal signals for manipulation. Our sensor features a fully transparent elastomer, persistent illumination, novel keyline markers, and efficient tracking, while our learning system integrates these signals through a Transformer-based Diffusion Policy. Experiments on five challenging real-world tasks show that TacThru-UMI achieves an average success rate of 85.5%, significantly outperforming the baselines of tactile policy(66.3%) and vision-only policy (55.4%). The system excels in critical scenarios, including contact detection with thin and soft objects and precision manipulation requiring multimodal coordination. This work demonstrates that combining simultaneous multimodal perception with modern learning frameworks enables more precise, adaptable robotic manipulation.

cs.RO↗

arXiv2026

Anyonic membranes and Pontryagin statistics

Anyons, unique to two spatial dimensions, underlie extraordinary phenomena such as the fractional quantum Hall effect, but their generalization to higher dimensions has remained elusive. The topology of Eilenberg-MacLane spaces constrains the loop statistics to be only bosonic or fermionic in any dimension. In this work, we introduce the novel anyonic statistics for membrane excitations in four dimensions. Analogous to the $\mathbb{Z}_N$-particle exhibiting $\mathbb{Z}_{N\times \gcd(2,N)}$ anyonic statistics in two dimensions, we show that the $\mathbb{Z}_N$-membrane possesses $\mathbb{Z}_{N\times \gcd(3,N)}$ anyonic statistics in four dimensions. Given unitary volume operators that create membrane excitations on the boundary, we propose an explicit 56-step unitary sequence that detects the membrane statistics. We further analyze the boundary theory of $(5{+}1)$D 1-form $\mathbb{Z}_N$ symmetry-protected topological phases and demonstrate that their domain walls realize all possible anyonic membrane statistics. We then show that the $\mathbb{Z}_3$ subgroup persists in all higher dimensions. In addition to the standard fermionic $\mathbb{Z}_2$ membrane statistics arising from Stiefel-Whitney classes, membranes also exhibit $\mathbb{Z}_3$ statistics associated with Pontryagin classes. We explicitly verify that the 56-step process detects the nontrivial $\mathbb{Z}_3$ statistics in 5, 6, and 7 spatial dimensions. Moreover, in 7 and higher dimensions, the statistics of membrane excitations stabilize to $\mathbb{Z}_{2} \times \mathbb{Z}_{3}$, with the $\mathbb{Z}_3$ sector consistently captured by this process.

quant-ph↗

arXiv2025

Branch Learning in MRI: More Data, More Models, More Training

We investigated two complementary strategies for multicontrast cardiac MR reconstruction: physics-consistent data-space augmentation (DualSpaceCMR) and parameter-efficient capacity scaling via VQPrompt and Moero. DualSpaceCMR couples image-level transforms with kspace noise and motion simulations while preserving forwardmodel consistency. VQPrompt adds a lightweight bottleneck prompt; Moero embeds a sparse mixture of experts within a deep unrolled network with histogram-based routing. In the multivendor, multisite CMRxRecon25 benchmark, we evaluate fewshot and out-of-distribution generalization. On small datasets, k-space motion-plus-noise improves reconstruction; on the large benchmark it degrades performance, revealing sensitivity to augmentation ratio and schedule. VQPrompt produces modest and consistent gains with negligible memory overhead. Moero continues to improve after early plateaus and maintains baseline-like fewshot and out-of-distribution behavior despite mild overfitting, but sparse routing lowers PyTorch throughput and makes wall clock time the main bottleneck. These results motivate scale-aware augmentation and suggest prompt-based capacity scaling as a practical path, while efficiency improvements are crucial for sparse expert models.

eess.IV↗

arXiv2025

Variational Continual Test-Time Adaptation

Continual Test-Time Adaptation (CTTA) task investigates effective domain adaptation under the scenario of continuous domain shifts during testing time. Due to the utilization of solely unlabeled samples, there exists significant uncertainty in model updates, leading CTTA to encounter severe error accumulation issues. In this paper, we introduce VCoTTA, a variational Bayesian approach to measure uncertainties in CTTA. At the source stage, we transform a pretrained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model. During the testing time, we employ a mean-teacher update strategy using variational inference for the student model and exponential moving average for the teacher model. Our novel approach updates the student model by combining priors from both the source and teacher models. The evidence lower bound is formulated as the cross-entropy between the student and teacher models, along with the Kullback-Leibler (KL) divergence of the prior mixture. Experimental results on three datasets demonstrate the method's effectiveness in mitigating error accumulation within the CTTA framework.

cs.LG↗

arXiv2025

Ternary-Input Binary-Weight CNN Accelerator Design for Miniature Object Classification System with Query-Driven Spatial DVS

Miniature imaging systems are essential for space-constrained applications but are limited by memory and power constraints. While machine learning can reduce data size by extracting key features, its high energy demands often exceed the capacity of small batteries. This paper presents a CNN hardware accelerator optimized for object classification in miniature imaging systems. It processes data from a spatial Dynamic Vision Sensor (DVS), reconfigurable to a temporal DVS via pixel sharing, minimizing sensor area. By using ternary DVS outputs and a ternary-input, binary-weight neural network, the design reduces computation and memory needs. Fabricated in 28 nm CMOS, the accelerator cuts data size by 81% and MAC operations by 27%. It achieves 440 ms inference time at just 1.6 mW power consumption, improving the Figure-of-Merit (FoM) by 7.3x over prior CNN accelerators for miniature systems.

cs.AR↗

arXiv2025

JW-Flare: Accurate Solar Flare Forecasting Method Based on Multimodal Large Language Models

Solar flares, the most powerful explosive phenomena in the solar system, may pose significant hazards to spaceborne satellites and ground-based infrastructure. Despite decades of intensive research, reliable flare prediction remains a challenging task. Large Language Models, as a milestone in artificial intelligence, exhibit exceptional general knowledge and next-token prediction capabilities. Here we introduce JW-Flare, the first Multimodal Large Language Models (MLLMs) explicitly trained for solar flare forecasting through fine-tuning on textual physic parameters of solar active regions and magnetic field images. This method demonstrates state-of-the-art (SOTA) performance for large flares prediction on the test dataset. It effectively identifies all 79 X-class flares from 18,949 test samples, yielding a True Skill Statistic (TSS) of 0.95 and a True Positive Rate (TPR) of 1.00, outperforming traditional predictive models. We further investigate the capability origins of JW-Flare through explainability experiments, revealing that solar physics knowledge acquired during pre-training contributes to flare forecasting performance. Additionally, we evaluate models of different parameter scales, confirming the Scaling_Law of Large Language Models in domain-specific applications, such as solar physics. This study marks a substantial advance in both the scale and accuracy of solar flare forecasting and opens a promising avenue for AI-driven methodologies in broader scientific domains.

astro-ph.SR↗

arXiv2025

AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy

Astronomical image interpretation presents a significant challenge for applying multimodal large language models (MLLMs) to specialized scientific tasks. Existing benchmarks focus on general multimodal capabilities but fail to capture the complexity of astronomical data. To bridge this gap, we introduce AstroMMBench, the first comprehensive benchmark designed to evaluate MLLMs in astronomical image understanding. AstroMMBench comprises 621 multiple-choice questions across six astrophysical subfields, curated and reviewed by 15 domain experts for quality and relevance. We conducted an extensive evaluation of 25 diverse MLLMs, including 22 open-source and 3 closed-source models, using AstroMMBench. The results show that Ovis2-34B achieved the highest overall accuracy (70.5%), demonstrating leading capabilities even compared to strong closed-source models. Performance showed variations across the six astrophysical subfields, proving particularly challenging in domains like cosmology and high-energy astrophysics, while models performed relatively better in others, such as instrumentation and solar astrophysics. These findings underscore the vital role of domain-specific benchmarks like AstroMMBench in critically evaluating MLLM performance and guiding their targeted development for scientific applications. AstroMMBench provides a foundational resource and a dynamic tool to catalyze advancements at the intersection of AI and astronomy.

astro-ph.IM↗

arXiv2025

StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations

The exponential growth of large-scale telescope arrays has boosted time-domain astronomy development but introduced operational bottlenecks, including labor-intensive observation planning, data processing, and real-time decision-making. Here we present the StarWhisper Telescope system, an AI agent framework automating end-to-end astronomical observations for surveys like the Nearby Galaxy Supernovae Survey. By integrating large language models with specialized function calls and modular workflows, StarWhisper Telescope autonomously generates site-specific observation lists, executes real-time image analysis via pipelines, and dynamically triggers follow-up proposals upon transient detection. The system reduces human intervention through automated observation planning, telescope controlling and data processing, while enabling seamless collaboration between amateur and professional astronomers. Deployed across Nearby Galaxy Supernovae Survey's network of 10 amateur telescopes, the StarWhisper Telescope has detected transients with promising response times relative to existing surveys. Furthermore, StarWhisper Telescope's scalable agent architecture provides a blueprint for future facilities like the Global Open Transient Telescope Array, where AI-driven autonomy will be critical for managing 60 telescopes.

astro-ph.IM↗

arXiv2025

Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

Tactile sensing is crucial for achieving human-level robotic capabilities in manipulation tasks. As a promising solution, Vision-Based Tactile Sensors (VBTSs) offer high spatial resolution and cost-effectiveness, but present unique challenges in robotics for their complex physical characteristics and visual signal processing requirements. The lack of efficient and accurate simulation tools for VBTSs has significantly limited the scale and scope of tactile robotics research. We present Taccel, a high-performance simulation platform that integrates IPC and ABD to model robots, tactile sensors, and objects with both accuracy and unprecedented speed, achieving an 18-fold acceleration over real-time across thousands of parallel environments. Unlike previous simulators that operate at sub-real-time speeds with limited parallelization, Taccel provides precise physics simulation and realistic tactile signals while supporting flexible robot-sensor configurations through user-friendly APIs. Through extensive validation in object recognition, robotic grasping, and articulated object manipulation, we demonstrate precise simulation and successful sim-to-real transfer. These capabilities position Taccel as a powerful tool for scaling up tactile robotics research and development, potentially transforming how robots interact with and understand their physical environment.

cs.RO↗

arXiv2025

Embedding high-resolution touch across robotic hands enables adaptive human-like grasping

Developing robotic hands that adapt to real-world dynamics remains a fundamental challenge in robotics and machine intelligence. Despite significant advances in replicating human hand kinematics and control algorithms, robotic systems still struggle to match human capabilities in dynamic environments, primarily due to inadequate tactile feedback. To bridge this gap, we present F-TAC Hand, a biomimetic hand featuring high-resolution tactile sensing (0.1mm spatial resolution) across 70% of its surface area. Through optimized hand design, we overcome traditional challenges in integrating high-resolution tactile sensors while preserving the full range of motion. The hand, powered by our generative algorithm that synthesizes human-like hand configurations, demonstrates robust grasping capabilities in dynamic real-world conditions. Extensive evaluation across 600 real-world trials demonstrates that this tactile-embodied system significantly outperforms non-tactile-informed alternatives in complex manipulation tasks (p<0.0001). These results provide empirical evidence for the critical role of rich tactile embodiment in developing advanced robotic intelligence, offering new perspectives on the relationship between physical sensing capabilities and intelligent behavior.

cs.RO↗

arXiv2025

Tac-Man: Tactile-Informed Prior-Free Manipulation of Articulated Objects

Integrating robots into human-centric environments such as homes, necessitates advanced manipulation skills as robotic devices will need to engage with articulated objects like doors and drawers. Key challenges in robotic manipulation of articulated objects are the unpredictability and diversity of these objects' internal structures, which render models based on object kinematics priors, both explicit and implicit, inadequate. Their reliability is significantly diminished by pre-interaction ambiguities, imperfect structural parameters, encounters with unknown objects, and unforeseen disturbances. Here, we present a prior-free strategy, Tac-Man, focusing on maintaining stable robot-object contact during manipulation. Without relying on object priors, Tac-Man leverages tactile feedback to enable robots to proficiently handle a variety of articulated objects, including those with complex joints, even when influenced by unexpected disturbances. Demonstrated in both real-world experiments and extensive simulations, it consistently achieves near-perfect success in dynamic and varied settings, outperforming existing methods. Our results indicate that tactile sensing alone suffices for managing diverse articulated objects, offering greater robustness and generalization than prior-based approaches. This underscores the importance of detailed contact modeling in complex manipulation tasks, especially with articulated objects. Advancements in tactile-informed approaches significantly expand the scope of robotic applications in human-centric environments, particularly where accurate models are difficult to obtain. See additional material at https://tacman-aom.github.io.

cs.RO↗

arXiv2025

SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion

Link prediction in knowledge graphs requires integrating structural information and semantic context to infer missing entities. While large language models offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in structural sparsity and semantic ambiguity, especially under incomplete or zero-shot settings. To address these challenges, we propose SLiNT (Structure-aware Language model with Injection and coNtrastive Training), a modular framework that injects knowledge-graph-derived structural context into a frozen LLM backbone with lightweight LoRA-based adaptation for robust link prediction. Specifically, Structure-Guided Neighborhood Enhancement (SGNE) retrieves pseudo-neighbors to enrich sparse entities and mitigate missing context; Dynamic Hard Contrastive Learning (DHCL) introduces fine-grained supervision by interpolating hard positives and negatives to resolve entity-level ambiguity; and Gradient-Decoupled Dual Injection (GDDI) performs token-level structure-aware intervention while preserving the core LLM parameters. Experiments on WN18RR and FB15k-237 show that SLiNT achieves superior or competitive performance compared with both embedding-based and generation-based baselines, demonstrating the effectiveness of structure-aware representation learning for scalable knowledge graph completion.

cs.CL↗

arXiv2025

Enzyme-free in situ polymerization of conductive polymers catalyzed by porous Au@Ag nanowires for stretchable neural electrodes

In situ polymerization of conductive polymers (CPs) represents a transformative approach in bioelectronics, by enabling the controlled growth of electrically active materials right at the tissue or device surface to create seamless biotic-abiotic interfaces. Traditional CP deposition techniques often use high anodic potentials, non-physiological electrolytes, or strong oxidants, making them harmful to adjacent tissues. A possible solution is enzymatic polymerization which operates under milder conditions, but it is limited by the stability and activity window of the enzyme catalysts, low throughput, and challenges in spatially confining polymer growth. To resolve these issues, here we developed one-dimensional porous Au-coated Ag nanowires with horseradish peroxidase (HRP)-like catalytic properties, thereby for the first time enabling mild in situ enzyme-free polymerization of conductive polymers near neutral pH. The enzyme-free polymerization is demonstrated both in aqueous dispersions at pH=6 and in situ onto porous Au coated Ag nanowire based stretchable electrodes. Following enzyme-free catalytic polymerization, the electrically conducting polymer coating on the electrode greatly improves the impedance and achieves an impedance of 2.6 kOhm at 1 kHz for 50x50 um large electrodes.

physics.chem-ph↗

arXiv2025

Generalized Statistics on Lattices

The statistics of particles and extended excitations, such as loops and membranes, are fundamental to modern condensed matter physics, high-energy physics, and quantum information science, yet a comprehensive lattice-level framework for computing them remains elusive. In this work, we develop a universal microscopic method to determine the generalized statistics of Abelian excitations on lattices of arbitrary dimension, and demonstrate it by deriving the statistics of particles, loops, and membranes in up to three spatial dimensions. Our approach constructs a sequence of local unitary operators whose many-body Berry phase encodes the desired statistical invariant. The required sequence is generated automatically from the Smith normal form of locality constraints and therefore needs no extra physical input. We prove that the resulting invariants are quantized, provide an algorithm that computes them efficiently, and show how they unify familiar braiding and fusion data of particles while also uncovering new self- and mutual-statistics of loop and membrane excitations. We further demonstrate that each statistical invariant corresponds to an 't Hooft anomaly of a generalized symmetry; we show that a non-trivial invariant both (i) obstructs gauging that symmetry and (ii) forbids any short-range-entangled (symmetry-preserving) ground state. This establishes a precise connection between microscopic lattice anomalies and many-body dynamics, providing a generalization of the Lieb-Schultz-Mattis theorem that constrains a wide class of quantum lattice systems.

quant-ph↗

arXiv2025

LightCurve MoE: A Dynamic Sparse Routing Mixture-of-Experts Architecture for Efficient Stellar Light Curve Classification

The classification of stellar light curves has become a key task in modern time-domain astronomy, fueled by the rapid growth of data from large-scale surveys such as Kepler and TESS. Although deep learning models have achieved high accuracy in this area, their computational costs can limit scalability. To tackle this issue, we propose LightCurve MoE, a Mixture-of-Experts (MoE) architecture that combines dynamic sparse routing with a dual-gating mechanism to balance accuracy, efficiency, and robustness. Our model includes five specialized experts, each using a different feature extraction method-such as wavelet transforms, Gramian angular fields, and recurrence plots-to capture unique patterns in the light curves. A dual-gating mechanism evaluates these expert outputs by analyzing both frequency and time-domain features, allowing the model to adaptively weigh each expert's contribution. During inference, only the top 3 out of 5 experts are activated per sample using a Top-k routing strategy, reducing computational cost by 40% compared to dense models while preserving strong accuracy (96%). The model also includes entropy regularization and a technique to retain inactive experts during training, ensuring stable and effective learning. By combining sparse computation with multi-modal feature fusion, LightCurve MoE offers a scalable solution for future large-scale photometric surveys like LSST and Global Open Transient Telescope Array (GOTTA), where processing efficiency is crucial due to the massive volume of daily data.

astro-ph.IM↗

arXiv2025

Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models

While AI for Science (AI4S) serves as an analytical tool in the current research paradigm, it doesn't solve its core inefficiency. We propose "Agent for Science" (Agent4S)-the use of LLM-driven agents to automate the entire research workflow-as the true Fifth Scientific Paradigm. This paper introduces a five-level classification for Agent4S, outlining a clear roadmap from simple task automation to fully autonomous, collaborative "AI Scientists." This framework defines the next revolutionary step in scientific discovery.

cs.AI↗