publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- On the Universal Structure in Deterministic Generative DiffusionarXiv preprint arXiv:2611.10338, 2026An earlier version of this work (April 2026), developed with minimal AI input, is available here.
Diffusion-based generative modeling has emerged as a general computational framework for simulating high-dimensional, structured data across various domains. Understanding its generative mechanisms is paramount for advancing model training and inference in a principled way. Here, we demonstrate that deterministic sampling trajectories share a universal geometric structure invariant to data modalities and diffusion model implementations. This structure can be largely explained by an exactly solvable model based on the optimal linear denoiser.
@article{chen2026universal, title = {On the Universal Structure in Deterministic Generative Diffusion}, author = {Chen, Defang and Zhou, Zhenyu and Wang, Can and Zheng, Zeyu and Lyu, Siwei}, journal = {arXiv preprint arXiv:2611.10338}, year = {2026}, } - LEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear LeapsIn Proceedings of the ACM International Conference on Multimedia, 2026
Diffusion models primarily rely on general-purpose ODE-based numerical methods for training-free accelerated sampling, but performance degrades with coarse time discretization. In this paper, we propose optimal linear leaps (LEAP), a specialized method grounded in theoretical and empirical investigations of sampling trajectory geometry. Built upon low-dimensionality and cross-trajectory consistency, LEAP formulates a supervised least-squares optimization problem within the local trajectory subspace, achieving a precise approximation of future states without model evaluations. Extensive experiments demonstrate that LEAP outperforms previous methods across diverse modalities, including text-to-image (Stable Diffusion 3.5, FLUX.1-dev) and image-to-3D (TRELLIS.2) generation. Furthermore, LEAP can be seamlessly integrated into existing solver-based methods, offering a plug-and-play enhancement for modern diffusion models.
@inproceedings{zheng2026leap, title = {LEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear Leaps}, author = {Zheng, Haowei and Zhou, Zhenyu and Chen, Jiawei and Wang, Can and Chen, Defang}, booktitle = {Proceedings of the ACM International Conference on Multimedia}, pages = {15616--15625}, year = {2026}, doi = {10.1145/3767308.3836106}, } - DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance DecouplingarXiv preprint arXiv:2609.34237, 2026
Flow-based image editing (FlowEdit) enables inversion-free semantic changes through the difference between source and target velocities. In this paper, we observe that FlowEdit’s default classifier-free guidance (CFG) configuration, with asymmetric source and target scales, causes substantial background leakage. Matching these guidance scales, for example by removing CFG, improves edit-relevant localization but severely degrades editability. To get the best of both worlds, we propose DecFlowEdit, which decouples the optimal guidance scales for localization and for editing in flow-based generative models. In particular, DecFlowEdit first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CFG. Our method remains training-free and inversion-free, requiring neither external spatial masks nor attention manipulation. Experiments on PIE-Bench across FLUX, SD3, and SD3.5 show that DecFlowEdit improves background preservation, reducing structure distance by approximately 61 to 73 percent and background LPIPS by 68 to 80 percent relative to FlowEdit at comparable editing fidelity.
@article{zhan2026decflowedit, title = {DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling}, author = {Zhan, Zheyuan and Wang, Can and Chen, Jiawei and Chen, Chun and Lyu, Siwei and Zheng, Zeyu and Chen, Defang}, journal = {arXiv preprint arXiv:2609.34237}, year = {2026}, } - Spectral Amplitude Purification in Distribution Matching for Diffusion DistillationarXiv preprint arXiv:2609.29116, 2026
Distribution Matching Distillation (DMD) enables high-quality diffusion sampling in only a few steps, but its optimization dynamics remain dominated by coarse, low-frequency signals, delaying the recovery of fine-grained details. We identify a pronounced concentration of spectral amplitudes at low frequencies in the DMD directional error, where dominant low-frequency components overwhelm weaker mid- and high-frequency signals. To address this issue, we propose Spectral Amplitude Purification for Distribution Matching Distillation (SAP-DMD), a plug-and-play approach that adaptively modulates the amplitude spectrum of the DMD directional field. By suppressing the dominant tail of the amplitude spectrum, SAP-DMD reduces low-frequency dominance and promotes more effective recovery of fine structures and textures. Experiments on PixArt-α, SD3, and SD3.5 demonstrate that SAP-DMD accelerates training convergence and improves generation quality under both 2-step and 4-step sampling.
@article{zhou2026spectral, title = {Spectral Amplitude Purification in Distribution Matching for Diffusion Distillation}, author = {Zhou, Zhenyu and Wang, Can and Chen, Chun and Zheng, Zeyu and Chen, Defang}, journal = {arXiv preprint arXiv:2609.29116}, year = {2026}, } - Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion ModelsIn European Conference on Computer Vision, 2026
Text-to-image diffusion models have achieved unprecedented success but still struggle to produce high-quality results under limited sampling budgets. Existing training-free sampling acceleration methods are typically developed independently, leaving the overall performance and compatibility among these methods unexplored. In this paper, we bridge this gap by systematically elucidating the design space, and our comprehensive experiments identify the sampling time schedule as the most pivotal factor. Inspired by the geometric properties of diffusion models revealed through the Frenet-Serret formulas, we propose constant total rotation schedule (TORS), a scheduling strategy that ensures uniform geometric variation along the sampling trajectory. TORS outperforms previous training-free acceleration methods and produces high-quality images with 10 sampling steps on Flux.1-Dev and Stable Diffusion 3.5. Extensive experiments underscore the adaptability of our method to unseen models, hyperparameters, and downstream applications.
@inproceedings{zhou2026tors, title = {Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models}, author = {Zhou, Zhenyu and Chen, Defang and Lyu, Siwei and Chen, Chun and Wang, Can}, booktitle = {European Conference on Computer Vision}, year = {2026} }
2025
- Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative ModelsJournal of Statistical Mechanics: Theory and Experiment, 2025Top-tier journal in Statistical Mechanics. Published more than 30 papers from the Nobel Laureate Giorgio Parisi (Physics, 2021).
Diffusion-based generative models employ stochastic differential equations (SDEs) and their equivalent probability flow ordinary differential equations (ODEs) to establish a smooth transformation between complex high-dimensional data distributions and tractable prior distributions. In this paper, we reveal a striking geometric regularity in the deterministic sampling dynamics: each simulated sampling trajectory lies within an extremely low-dimensional subspace, and all trajectories exhibit an almost identical ”boomerang” shape, regardless of the model architecture, applied conditions, or generated content. We characterize several intriguing properties of these trajectories, particularly under closed-form solutions based on kernel-estimated data modeling. We also demonstrate a practical application of the discovered trajectory regularity by proposing a dynamic programming-based scheme to better align the sampling time schedule with the underlying trajectory structure. This simple strategy requires minimal modification to existing ODE-based numerical solvers, incurs negligible computational overhead, and achieves superior image generation performance, especially in regions with only 5-10 function evaluations.
@article{chen2025geometric, title = {Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative Models}, author = {Chen, Defang and Zhou, Zhenyu and Wang, Can and Lyu, Siwei}, journal = {Journal of Statistical Mechanics: Theory and Experiment}, volume = {2025}, number = {12}, pages = {124002}, year = {2025}, publisher = {IOP Publishing}, } - Fully AI-Generated Image Detection: Definition, Recent Advances and Challengesarxiv, 2025
@article{xu2025detection, title = {Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges}, author = {Xu, Qijie and Wang, Can and Chen, Jiawei and Lyu, Siwei and Chen, Defang}, journal = arxiv, year = {2025}, } - DICE: Distilling Classifier-Free Guidance into Text EmbeddingsIn Proceedings of the AAAI Conference on Artificial Intelligence, 2025Oral, 4.7%
Text-to-image diffusion models are capable of generating high-quality images, but these images often fail to align closely with the given text prompts. Classifier-free guidance (CFG) is a popular and effective technique for improving text-image alignment in the generative process. However, using CFG introduces significant computational overhead and deviates from the established theoretical foundations of diffusion models. In this paper, we present DIstilling CFG by enhancing text Embeddings (DICE), a novel approach that removes the reliance on CFG in the generative process while maintaining the benefits it provides. DICE distills a CFG-based text-to-image diffusion model into a CFG-free version by refining text embeddings to replicate CFG-based directions. In this way, we avoid the computational and theoretical drawbacks of CFG, enabling high-quality, well-aligned image generation at a fast sampling speed. Extensive experiments on multiple Stable Diffusion v1.5 variants, SDXL and PixArt-αdemonstrate the effectiveness of our method. Furthermore, DICE supports negative prompts for image editing to improve image quality further.
@inproceedings{zhou2026dice, title = {DICE: Distilling Classifier-Free Guidance into Text Embeddings}, author = {Zhou, Zhenyu and Chen, Defang and Wang, Can and Chen, Chun and Lyu, Siwei}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2025} } - Conditional Image Synthesis with Diffusion Models: A SurveyZheyuan Zhan, Defang Chen†, Jian-Ping Mei, Zhenghe Zhao, Jiawei Chen, Chun Chen, Siwei Lyu, and Can WangTransactions on Machine Learning Research, 2025
Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis, leading to exponential growth in the literature. However, the complexity of diffusion-based modeling, the wide range of image synthesis tasks, and the diversity of conditioning mechanisms present significant challenges for researchers to keep up with rapid developments and to understand the core concepts on this topic. In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, i.e., the denoising network and the sampling process. We specifically highlight the underlying principles, advantages, and potential challenges of various conditioning approaches during the training, re-purposing, and specialization stages to construct a desired denoising network. We also summarize six mainstream conditioning mechanisms in the sampling process. All discussions are centered around popular applications. Finally, we pinpoint several critical yet still unsolved problems and suggest some possible solutions for future research.
@article{zhan2025conditional, title = {Conditional Image Synthesis with Diffusion Models: A Survey}, author = {Zhan, Zheyuan and Chen, Defang and Mei, Jian-Ping and Zhao, Zhenghe and Chen, Jiawei and Chen, Chun and Lyu, Siwei and Wang, Can}, journal = {Transactions on Machine Learning Research}, year = {2025}, } - Knowledge distillation with refined logitsIn Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address the limitations of current logit distillation methods. Our approach is motivated by the observation that even high-performing teacher models can make incorrect predictions, creating an exacerbated divergence between the standard distillation loss and the cross-entropy loss, which can undermine the consistency of the student model’s learning objectives. Previous attempts to use labels to empirically correct teacher predictions may undermine the class correlations. In contrast, our RLD employs labeling information to dynamically refine teacher logits. In this way, our method can effectively eliminate misleading information from the teacher while preserving crucial class correlations, thus enhancing the value and efficiency of distilled knowledge. Experimental results on CIFAR-100 and ImageNet demonstrate its superiority over existing methods.
@inproceedings{sun2025knowledge, title = {Knowledge distillation with refined logits}, author = {Sun, Wujie and Chen, Defang and Lyu, Siwei and Chen, Genlang and Chen, Chun and Wang, Can}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages = {1110--1119}, year = {2025} }
2024
- Simple and fast distillation of diffusion modelsIn Advances in Neural Information Processing Systems, 2024
Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based accelerated sampling methods have been developed recently. However, they generally require time-consuming fine tuning with elaborate designs to achieve satisfactory performance in a specific number of function evaluation (NFE), making them difficult to employ in practice. To address this issue, we propose Simple and Fast Distillation (SFD) of diffusion models, which simplifies the paradigm used in existing methods and largely shortens their fine-tuning time up to 1000 . We begin with a vanilla distillation-based sampling method and boost its performance to state of the art by identifying and addressing several small yet vital factors affecting the synthesis efficiency and quality. Our method can also achieve sampling with variable NFEs using a single distilled model. Extensive experiments demonstrate that SFD strikes a good balance between the sample quality and fine-tuning costs in few-step image generation task. For example, SFD achieves 4.53 FID (NFE=2) on CIFAR-10 with only 0.64 hours of fine-tuning on a single NVIDIA A100 GPU.
@inproceedings{zhou2024simple, title = {Simple and fast distillation of diffusion models}, author = {Zhou, Zhenyu and Chen, Defang and Wang, Can and Chen, Chun and Lyu, Siwei}, booktitle = {{Advances in Neural Information Processing Systems}}, pages = {40831--40860}, year = {2024}, } - On the Trajectory Regularity of ODE-based Diffusion SamplingIn International Conference on Machine Learning, 2024
Diffusion-based generative models use stochastic differential equations (SDEs) and their equivalent ordinary differential equations (ODEs) to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models. We characterize an implicit denoising trajectory and discuss its vital role in forming the coupled sampling trajectory with a strong shape regularity, regardless of the generated content. We also describe a dynamic programming-based scheme to make the time schedule in sampling better fit the underlying trajectory structure. This simple strategy requires minimal modification to any given ODE-based numerical solvers and incurs negligible computational cost, while delivering superior performance in image generation, especially in 5∼10 function evaluations.
@inproceedings{chen2024trajectory, title = {On the Trajectory Regularity of ODE-based Diffusion Sampling}, author = {Chen, Defang and Zhou, Zhenyu and Wang, Can and Shen, Chunhua and Lyu, Siwei}, booktitle = {International Conference on Machine Learning}, pages = {7905--7934}, year = {2024}, } - Fast ODE-based Sampling for Diffusion Models in Around 5 StepsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible. Recently, various fast samplers utilizing higher-order ODE solvers have emerged and achieved better performance than the initial first-order one. However, these numerical methods inherently result in certain approximation errors, which significantly degrades sample quality with extremely small NFE (e.g., around 5). In contrast, based on the geometric observation that each sampling trajectory almost lies in a two-dimensional subspace embedded in the ambient space, we propose Approximate MEan-Direction Solver (AMED-Solver) that eliminates truncation errors by directly learning the mean direction for fast diffusion sampling. Besides, our method can be easily used as a plugin to further improve existing ODE-based samplers. Extensive experiments on image synthesis with the resolution ranging from 32 to 512 demonstrate the effectiveness of our method. With only 5 NFE, we achieve 6.61 FID on CIFAR-10, 10.74 FID on ImageNet 64\times64, and 13.20 FID on LSUN Bedroom.
@inproceedings{zhou2024fast, title = {Fast ODE-based Sampling for Diffusion Models in Around 5 Steps}, author = {Zhou, Zhenyu and Chen, Defang and Wang, Can and Chen, Chun}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages = {7777--7786}, year = {2024}, } - Knowledge Distillation on Deep Neural NetworksZhejiang University, Outstanding Doctoral Dissertation award (Top 2%)
2023
- A Geometric Perspective on Diffusion ModelsarXiv preprint arXiv:2305.19947, 2023The earliest work connecting Mean Shift and Diffusion Models.
Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochastic differential equations (SDEs) and their marginal-preserving ordinary differential equations (ODEs) to describe data perturbation and generative modeling in a unified framework. In this paper, we carefully inspect the ODE-based sampling of a popular variance-exploding SDE and reveal several intriguing structures of its sampling dynamics. We discover that the data distribution and the noise distribution are smoothly connected with a quasi-linear sampling trajectory and another implicit denoising trajectory that even converges faster. Meanwhile, the denoising trajectory governs the curvature of the corresponding sampling trajectory and its finite differences yield various second-order samplers used in practice. Furthermore, we establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm, with which we can characterize the asymptotic behavior of diffusion models and identify the empirical score deviation.
@article{chen2023geometric, title = {A Geometric Perspective on Diffusion Models}, author = {Chen, Defang and Zhou, Zhenyu and Mei, Jian-Ping and Shen, Chunhua and Chen, Chun and Wang, Can}, journal = {arXiv preprint arXiv:2305.19947}, year = {2023}, }
2022
- Knowledge Distillation with the Reused Teacher ClassifierIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years, generally with elaborately designed knowledge representations, which in turn increase the difficulty of model development and interpretation. In contrast, we empirically show that a simple knowledge distillation technique is enough to significantly narrow down the teacher-student performance gap. We directly reuse the discriminative classifier from the pre-trained teacher model for student inference and train a student encoder through feature alignment with a single \ell_2 loss. In this way, the student model is able to achieve exactly the same performance as the teacher model provided that their extracted features are perfectly aligned. An additional projector is developed to help the student encoder match with the teacher classifier, which renders our technique applicable to various teacher and student architectures. Extensive experiments demonstrate that our technique achieves state-of-the-art results at the modest cost of compression ratio due to the added projector
@inproceedings{chen2022simkd, title = {Knowledge Distillation with the Reused Teacher Classifier}, author = {Chen, Defang and Mei, Jian-Ping and Zhang, Hailin and Wang, Can and Feng, Yan and Chen, Chun}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages = {11933--11942}, year = {2022}, } - Confidence-aware multi-teacher knowledge distillationHailin Zhang, Defang Chen, and Can WangIn IEEE International Conference on Acoustics, Speech and Signal Processing, 2022
Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources from multiple teachers. However, existing studies mainly integrate knowledge from diverse sources by averaging over multiple teacher predictions or combining them using other label-free strategies, which may mislead student in the presence of low-quality teacher predictions. To tackle this problem, we propose Confidence-Aware Multi-teacher Knowledge Distillation (CA-MKD), which adaptively assigns sample-wise reliability for each teacher prediction with the help of ground-truth labels, with those teacher predictions close to one-hot labels assigned large weights. Besides, CA-MKD incorporates features in intermediate layers to stable the knowledge transfer process. Extensive experiments show our CA-MKD consistently outperforms all compared state-of-the-art methods across various teacher-student architectures.
@inproceedings{zhang2022confidence, title = {Confidence-aware multi-teacher knowledge distillation}, author = {Zhang, Hailin and Chen, Defang and Wang, Can}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing}, pages = {4498--4502}, year = {2022}, }
2021
- Distilling holistic knowledge with graph neural networksSheng Zhou, Yucheng Wang, Defang Chen, Jiawei Chen, Xin Wang, Can Wang, and Jiajun BuIn Proceedings of the IEEE/CVF international conference on computer vision, 2021
Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network. Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the relational knowledge. However, these two types of knowledge are usually modeled independently while the inherent correlations between them are largely ignored. It is critical for sufficient student network learning to integrate both individual knowledge and relational knowledge while reserving their inherent correlation. In this paper, we propose to distill the novel holistic knowledge based on an attributed graph constructed among instances. The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner. Extensive experiments and ablation studies are conducted on benchmark datasets, the results demonstrate the effectiveness of the proposed method.
@inproceedings{zhou2021distilling, title = {Distilling holistic knowledge with graph neural networks}, author = {Zhou, Sheng and Wang, Yucheng and Chen, Defang and Chen, Jiawei and Wang, Xin and Wang, Can and Bu, Jiajun}, booktitle = {Proceedings of the IEEE/CVF international conference on computer vision}, pages = {10387--10396}, year = {2021}, } - Cross-Layer Distillation with Semantic CalibrationIn Proceedings of the AAAI Conference on Artificial Intelligence, 2021Journal version published in IEEE Trans. Knowl. Data Eng. (TKDE)
Highly-Cited Paper Indexed by 2024/2025 Google Scholar MetricsKnowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned teacher-student pairs in intermediate layers for further improvement. However, layer semantics may vary in different neural networks and semantic mismatch in manual layer associations will lead to performance degeneration due to negative regularization. To address this issue, we propose Semantic Calibration for cross-layer Knowledge Distillation (SemCKD), which automatically assigns proper target layers of the teacher model for each student layer with an attention mechanism. With a learned attention distribution, each student layer distills knowledge contained in multiple teacher layers rather than a specific intermediate layer for appropriate cross-layer supervision. We further provide theoretical analysis of the association weights and conduct extensive experiments to demonstrate the effectiveness of our approach.
@inproceedings{chen2021cross, author = {Chen, Defang and Mei, Jian{-}Ping and Zhang, Yuan and Wang, Can and Wang, Zhe and Feng, Yan and Chen, Chun}, title = {Cross-Layer Distillation with Semantic Calibration}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, pages = {7028--7036}, year = {2021}, }
2020
- Online Knowledge Distillation with Diverse PeersIn Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate predictions of multiple student models as targets to train each student model. Although group-derived targets give a good recipe for teacher-free distillation, group members are homogenized quickly with simple aggregation functions, leading to early saturated solutions. In this work, we propose Online Knowledge Distillation with Diverse peers (OKDDip), which performs two-level distillation during training with multiple auxiliary peers and one group leader. In the first-level distillation, each auxiliary peer holds an individual set of aggregation weights generated with an attention-based mechanism to derive its own targets from predictions of other auxiliary peers. Learning from distinct target distributions helps to boost peer diversity for effectiveness of group-based distillation. The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i.e., the model used for inference. Experimental results show that the proposed framework consistently gives better performance than state-of-the-art approaches without sacrificing training or inference complexity, demonstrating the effectiveness of the proposed two-level distillation framework.
@inproceedings{chen2020online, title = {Online Knowledge Distillation with Diverse Peers}, author = {Chen, Defang and Mei, Jian-Ping and Wang, Can and Feng, Yan and Chen, Chun}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, pages = {3430--3437}, year = {2020}, }