arXiv subjects

Cong Chen

Publications and source records attributed to Cong Chen.

At least 55 records · Page 3Linked to original sources

arXiv2025

Communications to Circulations: Real-Time 3D Wind Field Prediction Using 5G GNSS Signals and Deep Learning

Accurate atmospheric wind field information is crucial for various applications, including weather forecasting, aviation safety, and disaster risk reduction. However, obtaining high spatiotemporal resolution wind data remains challenging due to limitations in traditional in-situ observations and remote sensing techniques, as well as the computational expense and biases of numerical weather prediction (NWP) models. This paper introduces G-WindCast, a novel deep learning framework that leverages signal strength variations from 5G Global Navigation Satellite System (GNSS) signals to forecast three-dimensional (3D) atmospheric wind fields. The framework utilizes Forward Neural Networks (FNN) and Transformer networks to capture complex, nonlinear, and spatiotemporal relationships between GNSS-derived features and wind dynamics. Our preliminary results demonstrate promising accuracy in real-time wind forecasts (up to 30 minutes lead time). The model exhibits robustness across forecast horizons and different pressure levels, and its predictions for wind fields show superior agreement with ground-based radar wind profiler compared to concurrent European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5). Furthermore, we show that the system can maintain excellent performance for localized forecasting even with a significantly reduced number of GNSS stations (e.g., around 100), highlighting its cost-effectiveness and scalability. This interdisciplinary approach underscores the transformative potential of exploiting non-traditional data sources and deep learning for advanced environmental monitoring and real-time atmospheric applications.

cs.LG↗

arXiv2025

HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation

In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. This is realized through two key designs: (1) multi-scale downsampling applied to the token map generated by the tokenizer encoder, producing a sequence of multi-scale tokens, and (2) a scale-causal attention mechanism that enables the progressive flow of information from low-resolution global semantic features to high-resolution structural details. Coupling these designs, HieraTok achieves significant improvements in both image reconstruction and generation tasks. Under identical settings, the multi-scale visual tokenizer outperforms its single-scale counterpart by a 27.2\% improvement in rFID ($1.47 \rightarrow 1.07$). When integrated into downstream generation frameworks, it achieves a $1.38\times$ faster convergence rate and an 18.9\% boost in gFID ($16.4 \rightarrow 13.3$), which may be attributed to the smoother and more uniformly distributed latent space. Furthermore, by scaling up the tokenizer's training, we demonstrate its potential by a sota rFID of 0.45 and a gFID of 1.82 among ViT tokenizers. To the best of our knowledge, we are the first to introduce multi-scale ViT-based tokenizer in image reconstruction and image generation. We hope our findings and designs advance the ViT-based tokenizers in visual generation tasks.

cs.CV↗

arXiv2025

GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks

Autonomous agents for long-sequence Graphical User Interface tasks are hindered by sparse rewards and the intractable credit assignment problem. To address these challenges, we introduce GUI-Shepherd, a Process Reward Model that provides dense, step-by-step feedback to guide agents. GUI-Shepherd is trained on a diverse large-scale data set of $52$k interactions that features human-annotated scores and GPT-4o generated rationales, enabling it to serve both as a reward provider for RL training and as a verifier for inference. As far as we know, we are the first to conduct a systematic study of process supervision in GUI agents, across diverse settings from online long-horizon tasks to offline single-step prediction. On the online AndroidWorld benchmark, GUI-Shepherd improves success rate by $7.7$ points via multi-turn online PPO, significantly outperforming Outcome Reward Model based competitors. When used as an inference verifier, it brings $5.1$ points improvements. The benefits generalize to the offline AndroidControl benchmark, with gains of $2.2$ points as a reward provider and $4.3$ points as a verifier. Collectively, our results establish that high-fidelity process supervision is critical for building more capable GUI agents and present a generalizable solution.

cs.AI↗

arXiv2025

LongCat-Flash Technical Report

We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming from the need for scalable efficiency, LongCat-Flash adopts two novel designs: (a) Zero-computation Experts, which enables dynamic computational budget allocation and activates 18.6B-31.3B (27B on average) per token depending on contextual demands, optimizing resource usage. (b) Shortcut-connected MoE, which enlarges the computation-communication overlap window, demonstrating notable gains in inference efficiency and throughput compared to models of a comparable scale. We develop a comprehensive scaling framework for large models that combines hyperparameter transfer, model-growth initialization, a multi-pronged stability suite, and deterministic computation to achieve stable and reproducible training. Notably, leveraging the synergy among scalable architectural design and infrastructure efforts, we complete model training on more than 20 trillion tokens within 30 days, while achieving over 100 tokens per second (TPS) for inference at a cost of \$0.70 per million output tokens. To cultivate LongCat-Flash towards agentic intelligence, we conduct a large-scale pre-training on optimized mixtures, followed by targeted mid- and post-training on reasoning, code, and instructions, with further augmentation from synthetic data and tool use tasks. Comprehensive evaluations demonstrate that, as a non-thinking foundation model, LongCat-Flash delivers highly competitive performance among other leading models, with exceptional strengths in agentic tasks. The model checkpoint of LongCat-Flash is open-sourced to foster community research. LongCat Chat: https://longcat.ai Hugging Face: https://huggingface.co/meituan-longcat GitHub: https://github.com/meituan-longcat

cs.CL↗

arXiv2025

Real-Time Defense Against Coordinated Cyber-Physical Attacks: A Robust Constrained Reinforcement Learning Approach

Modern power systems face increasing vulnerability to sophisticated cyber-physical attacks beyond traditional N-1 contingency frameworks. Existing security paradigms face a critical bottleneck: efficiently identifying worst-case scenarios and rapidly coordinating defensive responses are hindered by intensive computation and time delays, during which cascading failures can propagate. This paper presents a novel tri-level robust constrained reinforcement learning (RCRL) framework for robust power system security. The framework generates diverse system states through AC-OPF formulations, identifies worst-case N-K attack scenarios for each state, and trains policies to mitigate these scenarios across all operating conditions without requiring predefined attack patterns. The framework addresses constraint satisfaction through Beta-blending projection-based feasible action mapping techniques during training and primal-dual augmented Lagrangian optimization for deployment. Once trained, the RCRL policy learns how to control observed cyber-physical attacks in real time. Validation on IEEE benchmark systems demonstrates effectiveness against coordinated N-K attacks, causing widespread cascading failures throughout the network. The learned policy can successfully respond rapidly to recover system-wide constraints back to normal within 0.21 ms inference times, establishing superior resilience for critical infrastructure protection.

eess.SY↗

arXiv2025

A Steel Surface Defect Detection Method Based on Lightweight Convolution Optimization

Surface defect detection of steel, especially the recognition of multi-scale defects, has always been a major challenge in industrial manufacturing. Steel surfaces not only have defects of various sizes and shapes, which limit the accuracy of traditional image processing and detection methods in complex environments. However, traditional defect detection methods face issues of insufficient accuracy and high miss-detection rates when dealing with small target defects. To address this issue, this study proposes a detection framework based on deep learning, specifically YOLOv9s, combined with the C3Ghost module, SCConv module, and CARAFE upsampling operator, to improve detection accuracy and model performance. First, the SCConv module is used to reduce feature redundancy and optimize feature representation by reconstructing the spatial and channel dimensions. Second, the C3Ghost module is introduced to enhance the model's feature extraction ability by reducing redundant computations and parameter volume, thereby improving model efficiency. Finally, the CARAFE upsampling operator, which can more finely reorganize feature maps in a content-aware manner, optimizes the upsampling process and ensures detailed restoration of high-resolution defect regions. Experimental results demonstrate that the proposed model achieves higher accuracy and robustness in steel surface defect detection tasks compared to other methods, effectively addressing defect detection problems.

eess.IV↗

arXiv2025

Topological domain-wall states from Umklapp scattering in twisted bilayer graphene

Twistronics, harnessing interlayer rotation to tailor electronic states in van der Waals materials, has predominantly focused on small-angle regime. Here, we unveil the pivotal role of intervalley Umklapp scattering in large-angle twisted bilayer graphene, which governs low-energy physics and drives unconventional band topology. By constructing symmetry-constrained effective $k\cdot p$ models for $\pm 21.8^{\circ}$-twisted bilayers, we demonstrate how structural chirality imprints distinct electronic responses. The $D_6$ configuration exhibits a gapped spectrum with chiral interlayer coupling, while $D_3$ symmetric stacking configuration displays semimetallic behavior. Crucially, chirality inversion creates topological domain-wall states, which manifest as counterpropagating pseudospin modes at interfaces between oppositely twisted regions. These states, absent in untwisted bilayers, emerge from a Jackiw-Rebbi-like mechanism tied to chirality reversal. Atomistic simulations confirm these topological states and demonstrate their robustness against symmetry-breaking perturbations. The interplay between twist-induced chirality and topology opens new pathways for engineering domain-wall states in twisted materials.

cond-mat.mes-hall↗

arXiv2025

EEG-based Epileptic Prediction via a Two-stage Channel-aware Set Transformer Network

Epilepsy is a chronic, noncommunicable brain disorder, and sudden seizure onsets can significantly impact patients' quality of life and health. However, wearable seizure-predicting devices are still limited, partly due to the bulky size of EEG-collecting devices. To relieve the problem, we proposed a novel two-stage channel-aware Set Transformer Network that could perform seizure prediction with fewer EEG channel sensors. We also tested a seizure-independent division method which could prevent the adjacency of training and test data. Experiments were performed on the CHB-MIT dataset which includes 22 patients with 88 merged seizures. The mean sensitivity before channel selection was 76.4% with a false predicting rate (FPR) of 0.09/hour. After channel selection, dominant channels emerged in 20 out of 22 patients; the average number of channels was reduced to 2.8 from 18; and the mean sensitivity rose to 80.1% with an FPR of 0.11/hour. Furthermore, experimental results on the seizure-independent division supported our assertion that a more rigorous seizure-independent division should be used for patients with abundant EEG recordings.

eess.SP↗

arXiv2025

Advancing Waterfall Plots for Cancer Treatment Response Assessment through Adjustment of Incomplete Follow-Up Time

Waterfall plots are a key tool in early phase oncology clinical studies for visualizing individual patients' tumor size changes and provide efficacy assessment. However, comparing waterfall plots from ongoing studies with limited follow-up to those from completed studies with long follow-up is challenging due to underestimation of tumor response in ongoing patients. To address this, we propose a novel adjustment method that projects the waterfall plot of an ongoing study to approximate its appearance with sufficient follow-up. Recognizing that waterfall plots are simply rotated survival functions of best tumor size reduction from the baseline (in percentage), we frame the problem in a survival analysis context and adjust weight of each ongoing patients in an interim look Kaplan-Meier curve by leveraging the probability of potential tumor response improvement (i.e., "censoring"). The probability of improvement is quantified through an incomplete multinomial model to estimate the best tumor size change occurrence at each scan time. The adjusted waterfall plots of experimental treatments from ongoing studies are suitable for comparison with historical controls from completed studies, without requiring individual-level data of those controls. A real-data example demonstrates the utility of this method for robust efficacy evaluations.

stat.AP↗

arXiv2025

Estimates for generalized fractional integrals associated with operators on Morrey--Campanato spaces

Let $\mathcal{L}$ be the infinitesimal generator of an analytic semigroup $\big\{e^{-t\mathcal L}\big\}_{t>0}$ satisfying the Gaussian upper bounds. For given $0<α<n$, let $\mathcal L^{-α/2}$ be the generalized fractional integral associated with $\mathcal{L}$, which is defined as \begin{equation*} \mathcal L^{-α/2}(f)(x):=\frac{1}{Γ(α/2)}\int_0^{+\infty} e^{-t\mathcal L}(f)(x)t^{α/2-1}dt, \end{equation*} where $Γ(\cdot)$ is the usual gamma function. For a locally integrable function $b(x)$ defined on $\mathbb R^n$, the related commutator operator $\big[b,\mathcal L^{-α/2}\big]$ generated by $b$ and $\mathcal{L}^{-α/2}$ is defined by \begin{equation*} \big[b,\mathcal L^{-α/2}\big](f)(x):=b(x)\cdot\mathcal{L}^{-α/2}(f)(x)-\mathcal{L}^{-α/2}(bf)(x). \end{equation*} A new class of Morrey--Campanato spaces associated with $\mathcal{L}$ is introduced in this paper. The authors establish some new estimates for the commutators $\big[b,\mathcal L^{-α/2}\big]$ on Morrey--Campanato spaces. The corresponding results for higher-order commutators$\big[b,\mathcal L^{-α/2}\big]^m$($m\in \mathbb{N}$) are also discussed.

math.CA↗

arXiv2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

cs.LG↗

arXiv2025

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we identify the current lack of a metric that finely measures the caption quality in concept level. We hereby introduce HalFscore, a novel metric built upon the language graph and is designed to evaluate both the accuracy and completeness of dense captions at a granular level. Additionally, we identify the root cause of hallucination as the model's over-reliance on its language prior. To address this, we propose PerturboLLaVA, which reduces the model's reliance on the language prior by incorporating adversarially perturbed text during training. This method enhances the model's focus on visual inputs, effectively reducing hallucinations and producing accurate, image-grounded descriptions without incurring additional computational overhead. PerturboLLaVA significantly improves the fidelity of generated captions, outperforming existing approaches in handling multimodal hallucinations and achieving improved performance across general multimodal benchmarks.

cs.CV↗

arXiv2025

Adjustment for Inconsistency in Adaptive Phase 2/3 Designs with Dose Optimization

Adaptive Phase 2/3 designs hold great promise in contemporary oncology drug development, especially when limited data from Phase 1 dose-finding is insufficient for identifying an optimal dose. However, there is a general concern about inconsistent results before and after the adaptation. The imperfection in dose selection further complicates the issue. In this paper, we explicitly incorporate the concerns about inconsistency into the statistical analysis under three hypothesis testing strategies. This investigation paves the way for further research in a less explored area.

stat.AP↗

arXiv2025

Uncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks

Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities, and improve object detection accuracy compared with individual perception. However, adversarial attacks pose a potential threat to the deep learning COD models, and introduce high output uncertainty. With unknown attack models, it becomes even more challenging to improve COD resiliency and quantify the output uncertainty for highly dynamic perception scenes such as autonomous vehicles. In this study, we propose the Trusted Uncertainty Quantification in Collaborative Perception framework (TUQCP). TUQCP leverages both adversarial training and uncertainty quantification techniques to enhance the adversarial robustness of existing COD models. More specifically, TUQCP first adds perturbations to the shared information of randomly selected agents during object detection collaboration by adversarial training. TUQCP then alleviates the impacts of adversarial attacks by providing output uncertainty estimation through learning-based module and uncertainty calibration through conformal prediction. Our framework works for early and intermediate collaboration COD models and single-agent object detection models. We evaluate TUQCP on V2X-Sim, a comprehensive collaborative perception dataset for autonomous driving, and demonstrate a 80.41% improvement in object detection accuracy compared to the baselines under the same adversarial attacks. TUQCP demonstrates the importance of uncertainty quantification to COD under adversarial attacks.

cs.CV↗

arXiv2025

Spinless topological chirality from Umklapp scattering in twisted 3D structures

Spinless systems exhibit unique topological characteristics compared to spinful ones, stemming from their distinct algebra. Without chiral interactions typically linked to spin, an intriguing yet unexplored interplay between topological and structural chirality may be anticipated. Here we discover spinless topological chiralities solely from structural chiralities that lie in the 3D spatial patterning of structureless units, exemplified using two types of twisted graphite systems. In a 3D screw twisted structure without periodicity in all directions, we find a chiral Weyl semimetal phase where bulk topology and chiral surface states are both determined by the screw direction. And in a 3D periodic structure formed with layer-alternating twist angle signs, a higher-order Dirac semimetal with chiral hinge states is discovered. Underlying these novel topological states is the intervalley Umklapp scattering that captures the chirality of the twisted interfaces, leading effectively to a sign-flipped chiral interlayer hopping, thereby introducing $π$-flux Z2 lattice gauge field that alters the symmetry algebra. Our findings point to a new pathway for engineering topological chirality through patterning twisted arrays of featureless units, which can expand the design principles for topological photonics and acoustics.

cond-mat.mes-hall↗

arXiv2024

Adaptive Phase 2/3 Design with Dose Optimization

FDA's Project Optimus initiative for oncology drug development emphasizes selecting a dose that optimizes both efficacy and safety. When an inferentially adaptive Phase 2/3 design with dose selection is implemented to comply with the initiative, the conventional inverse normal combination test is commonly used for Type I error control. However, indiscriminate application of this overly conservative test can lead to substantial increase in sample size and timeline delays, which undermines the appeal of the adaptive approach. This, in turn, frustrates drug developers regarding Project Optimus. The inflation of Type I error depends on the probability of selecting a dose with better long-term efficacy outcome at end of the study based on limited follow-up data at dose selection. In this paper, we discuss the estimation of this probability and its impact on Type I error control in realistic settings. Incorporating it explicitly into the two methods we have proposed result in improved designs, potentially motivating drug developers to adhere more closely to an initiative that has the potential to revolutionize oncology drug development.

stat.AP↗

arXiv2024

Efficient Dynamic Attributed Graph Generation

Data generation is a fundamental research problem in data management due to its diverse use cases, ranging from testing database engines to data-specific applications. However, real-world entities often involve complex interactions that cannot be effectively modeled by traditional tabular data. Therefore, graph data generation has attracted increasing attention recently. Although various graph generators have been proposed in the literature, there are three limitations: i) They cannot capture the co-evolution pattern of graph structure and node attributes. ii) Few of them consider edge direction, leading to substantial information loss. iii) Current state-of-the-art dynamic graph generators are based on the temporal random walk, making the simulation process time-consuming. To fill the research gap, we introduce VRDAG, a novel variational recurrent framework for efficient dynamic attributed graph generation. Specifically, we design a bidirectional message-passing mechanism to encode both directed structural knowledge and attribute information of a snapshot. Then, the temporal dependency in the graph sequence is captured by a recurrence state updater, generating embeddings that can preserve the evolution pattern of early graphs. Based on the hidden node embeddings, a conditional variational Bayesian method is developed to sample latent random variables at the neighboring timestep for new snapshot generation. The proposed generation paradigm avoids the time-consuming path sampling and merging process in existing random walk-based methods, significantly reducing the synthesis time. Finally, comprehensive experiments on real-world datasets are conducted to demonstrate the effectiveness and efficiency of the proposed model.

cs.DB↗

arXiv2024

Generalized Design of Basket Trials with P-value Combination Test

The oncology exploratory basket trial design with pruning and pooling (P&P) approach has gained increasing popularity in recent years for its simplicity and efficiency. This method was proposed based on binary endpoint, limiting its wider application. This short communication proposed a generalized framework of using P-value combination test to implement pruning and pooling process in basket trials. Only P-values of any type of statistical testing from each cohort are needed for decision making, which provides great flexibility for basket trial designs with P&P approach.

stat.AP↗