Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks168 from public data
- ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification659
This paper proposes a new traffic representation model called Encrypted Traffic Bidirectional Encoder Representations from Transformer (ET-BERT), which pre-trains deep contextualized datagram-level representation from large-scale unlabeled data and achieves state-of-the-art performance across five encrypted traffic classification tasks.
- 575
- Shallow Attention Network for Polyp Segmentation443
The Shallow Attention Network (SANet) is proposed, which design the color exchange operation to decouple the image contents and colors, and force the model to focus more on the target shape and structure, and the shallow attention module to filter out the background noise of shallow features.
- 276
- InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring214
The non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals.
- Multi-compound Transformer for Accurate Biomedical Image Segmentation187
A unified transformer network, termed Multi-Compound Transformer (MCTrans), which incorporates rich feature learning and semantic structure mining into a unified framework and performs intra- and inter-scale self-attention, rather than single-scale attention in previous works.
- CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection154
This paper proposes a Contrastive Learning and Multi-Layer Fusion (CLMLF) method for multimodal sentiment detection, which first encode text and image to obtain hidden representations, and then uses a multi-layer fusion module to align and fuse the token-level features ofText and image.
- Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds125
This work proposes the BoxCloud, an informative and robust representation, to depict an object using the point-to-box relation, and designs an efficient box-aware feature fusion module, which leverages the aforementioned BoxCloud for reliable feature matching and embedding.
- X -Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning122
This study investigates a cross-modal knowledge transfer using Transformer for 3D dense captioning through the knowledge distillation enabled by a teacher-student framework and proposes X-Trans2Cap, which outperforms previous state-of-the-art models by a large margin.
- Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning113
DaC is presented, a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations and aligns the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy loss to reduce the distribution mismatch.
- Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds108
This work introduces a motion-centric paradigm to handle 3D SOT from a new perspective and proposes a matching-free two-stage tracker M2-Track, which significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS.
- SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training91
An asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE is built, which embeds skeleton joint sequence into graph convolutional network and reconstructs the masked skeleton joints and edges based on the prior human topology knowledge.
- Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning85
This article proposes to use the medical visual language BERT (Medical-VLBERT) model to identify the abnormality on the COVID-19 scans and generate the medical report automatically based on the detected lesion regions to produce more accurate medical reports.
- 80
- RoPGen77
Experimental results show that RoPGen can significantly improve the robustness of DL-based code authorship attribution, by respectively reducing 22.8% and 41.0% of the success rate of targeted and untargeted attacks on average.
- MMTN: Multi-Modal Memory Transformer Network for Image-Report Consistent Medical Report Generation67
A Multi-modal Memory Transformer Network (MMTN) is proposed to cope with multi- modal medical data for generating image-report consistent medical reports and achieves significant effectiveness over state-of-the-art approaches on both automatic metrics and human evaluation.
- 63
- Crystal structure of steroid reductase SRD5A reveals conserved steroid reduction mechanism63
Homology-based structural models of HsSRD5A1 and -2, together with biochemical characterization, define the substrate binding pocket of SRD5As, explain the properties of disease-related mutants and provide an important framework for further understanding of the mechanism of NADPH mediated steroids 3-oxo-Δ4 reduction.
- Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis51
This paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i.e., rendered or projected 2D images of the 3D object, to boost point cloud analysis.
- Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling50
Lumina-mGPT 2.0 is presented, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond, and is confirmed as a strong, flexible foundation model for unified multimodal generation.
- Composable Text Controls in Latent Space with ODEs47
A new efficient approach for composable text operations in the compact latent space of text, based on ordinary differential equations given arbitrary plug-in operators, which manages to generate or edit high-quality text substantially improving over previous methods in terms of generation quality and efficiency.
- 46
- Benchmarking the Robustness of LiDAR Semantic Segmentation Models44
A robust LiDAR segmentation model (RLSeg) is designed which greatly boosts the robustness with simple but effective modifications and can boost future research in robust LiDAR semantic segmentation for safety-critical applications.
- 39
- 34
- InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation32
Dense-sparse switchable attention framework InfLLM-V2 is introduced, a trainable sparse attention that seamlessly adapts models from short to long sequences, and an efficient implementation of InfLLM-V2 is introduced that significantly reduces the computational overhead.
- BoxPolyp: Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations32
A boosted BoxPolyp model to make full use of both accurate mask and extra coarse box annotations is proposed, which outperforms previous state-of-the-art methods by a large margin.
- Transformer based tooth classification from cone-beam computed tomography for dental charting32
A deep neuron network is built which accepts a 3D CBCT image patch that contains the region of interest (ROI) of a tooth as input and then outputs the type of the tooth, which outperforms other networks on 5 out of 6 3-dimensional medical image subsets.
- Achieving flexible fairness metrics in federated medical imaging31
Evaluated across four clinical applications (polyp segmentation, fundus vascular segmentation, cervical cancer segmentation, and skin disease diagnosis), FlexFair outperforms state-of theart methods in both fairness and accuracy.
- Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation31
The CLEVR3D is proposed, a large-scale VQA-3D dataset consisting of 171K questions from 8,771 3D scenes, and a question engine leveraging 3D scene graph structures to generate diverse reasoning questions, covering the questions of objects’ attributes and their spatial relationships is developed.
- 30
- 29
- A University Student Performance Prediction Model and Experiment Based on Multi-Feature Fusion and Attention Mechanism28
This study collected a triplet set of related courses and students’ real historical grades, proved the correlation between courses through data analysis, and verified the effectiveness of different dimensional features.
- UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation28
This paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network.
- 26
- Ultra Fine-Grained Image Semantic Embedding25
Graph-Regularized Image Semantic Embedding (Graph-RISE), a web-scale neural graph learning framework deployed at Google, which allows to train image embeddings to discriminate an unprecedented O(40M) ultra-fine-grained semantic labels, effectively captures semantics and differentiates nuances at levels that are closer to human-perception.
- 25
- Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation24
Experimental results show the novel Edit-Invariant Sequence Loss (EISL) method significantly outperforms the common CE loss and other strong baselines on all the tasks, and is easy to implement and efficient to compute with existing libraries.
- An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds23
Beyond 3D Siamese tracking, a motion-centric paradigm is introduced to handle LiDAR SOT from a new perspective and shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training.
- Learning to Search Efficiently in High Dimensions23
This paper considers a new framework that applies supervised learning to directly optimize a data structure that supports efficient large scale search and significantly outperforms the start-of-the-art learning to hash methods, as well as state of theart high dimensional search algorithms.
- Smart and Rapid Design of Nanophotonic Structures by an Adaptive and Regularized Deep Neural Network22
The proposed smart LRS-RCNN has been proven to greatly accelerate the design of photonic crystal structures as a state-of-the-art predictor for both Q-factor and V and can be modified and generalized to predict any type of optical properties for designing a wide range of different nanophotonic structures.
- 21
- Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains21
Experimental results demonstrate SST can effectively achieve promising universal human parsing performance as well as impressive improvements compared to its counterparts on three human parsing benchmarks (i.e., PASCAL-Person-Part, ATR, and CIHP).
- Ontology Representation of Online Shopping Customers Knowledge in Enterprise Information21
This paper constructs online shopping customers knowledge ontology model, and studies the knowledge representation based on the protégé environment.
- Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases20
This paper extends 3DVG to a more fine-grained and interpretable task, called 3D Phrase Aware Grounding (3DPAG), and achieves this through the proposed novel phrase-object alignment optimization and phrase-specific pre-training, boosting conventional 3D VG performance as well.
- Exemplar Normalization for Learning Deep Representation20
This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn different normalization methods for different convolutional layers and image samples of a deep network.
- ECC-PolypDet: Enhanced CenterNet With Contrastive Learning for Automatic Polyp Detection19
The Enhanced CenterNet with Contrastive Learning (ECC-PolypDet) is proposed, a two-stage training & end-to-end inference framework that leverages images and bounding box annotations to train a general model and fine-tune it based on the inference score to obtain a final robust model.
- Time–Memory Trade-Off Attack on the GSM A5/1 Stream Cipher Using Commodity GPGPU19
A unified TMTO cryptanalysis is presented, basing it on a unified rainbow table, then its general combination with distinguished points is described, and it is applied to the A5/1 stream cipher being used in the Global System for Mobile Communications (GSM).
- LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis18
This work builds a high-quality data synthesis pipeline based on Deepseek-R1 to curate LeX-10K, a dataset of 10K high-resolution, aesthetically refined 1024$\times$1024 images, and introduces LeX-Art, a comprehensive suite for high-quality text-image synthesis that systematically bridges the gap between prompt expressiveness and text rendering fidelity.
- 17
- 17
- Weakly Supervised Object Localization Through Inter-class Feature Similarity and Intra-class Appearance Consistency17
This paper proposes a simple but effective WSOL model through an inter-class feature similarity (ICFS) loss against the original cross entropy loss and achieves state-of-the-art performance on both CUB-200 and ImageNet-1K benchmarks.
- ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation16
ChartGalaxy is introduced, a million-scale dataset designed to advance the understanding and generation of infographic charts and provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.
- NG-NAS: Node growth neural architecture search for 3D medical image segmentation16
This work proposes a novel NAS algorithm called NG-NAS, which starts from a simple architecture with only 5 nodes, and greedily grows the best candidate node until meeting the constraint, and achieves state-of-the-art performance on public 3D medical image segmentation benchmarks.
- 16
- Toward Unpaired Multi-modal Medical Image Segmentation via Learning Structured Semantic Consistency15
This paper presents a novel scheme to learn the mutual benefits of different modalities to achieve better segmentation results for unpaired multi-modal medical images, designed as an external plug-and-play one, which can be discarded once the model is optimized.
- In-Context Compositional Generalization for Large Vision-Language Models11
A demonstration selection method to achieve ICCG for LVLMs is proposed, by considering two key factors of demonstrations: content and structure, from a multimodal perspective, and design a diversity-coverage-based matching score to select demonstrations with maximum coverage.
- 11
- 11
- 11
- Face recognition via local preserving average neighborhood margin maximization and extreme learning machine11
This paper extends ANMM to locality preserving average neighborhood margin maximization (LPANMM) in order to maintain the local structure on the original data manifold in the discriminant feature space and combines LPANMM with extreme learning machine (ELM) as a new scheme for face recognition.
- CrossBind: Collaborative Cross-Modal Identification of Protein Nucleic-Acid-Binding Residues10
This paper presents CrossBind, a novel collaborative cross modal approach for identifying binding residues by exploiting both protein geometric structure and its sequence prior knowledge extracted from a large scale protein language model that outperforms the next best state of the art methods on DNA and RNA datasets.
- 10
- Prior knowledge facilitates low homologous protein secondary structure prediction with DSM distillation10
The novel DSM-Distil is proposed, which takes advantage of the pretrained BERT and exploits the knowledge distillation on the newly designed dynamic scoring matrix (DSM) features to achieve the new state-of-the-art performance for low homologous proteins.
- COVID-19 risk assessment driven by urban spatiotemporal big data: a case study of Guangdong-Hong Kong-Macao Greater Bay Area10
The improved model introduces dynamic "return-to-work" population and propagation hotspots to calibrate COVID-19 parameters in different assessment units and improve SEIR model suitability in GBA; targeting on the urgent needs of high resolution risk assessment, the model utilizes multi-source urban big data and traditional epidemiological model to design an improved model.
- Hierarchical Weight Averaging for Deep Neural Networks9
This work first attempts to incorporate online and offline WA into a general training framework termed hierarchical WA, which is able to achieve both faster convergence speed and superior generalization performance without any fancy learning rate adjustment.
- CPU: Codebook Lookup Transformer with Knowledge Distillation for Point Cloud Upsampling9
A generic three-stage vector-quantization framework, which incorporates a Codebook lookup Transformer and knowledge distillation for Point Cloud Upsampling, named CPU, which outperforms state-of-the-art methods quantitatively and qualitatively.
- CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU9
This work conducts extensive experiments with four CTR prediction networks on two real-world datasets and successfully scaled 128 times the original batch size without accuracy loss, and develops the adaptive Column-wise Clipping (CowClip) to stabilize the training process in a large batch size setting.
- 9
- PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery9
A novel Locally Invertible Embedding (PointLIE) framework is proposed to unify the point cloud sampling and upsampling into one single framework through bi-directional learning and can theoretically guarantee the fidelity of reconstruction and outperform state-of-the-arts quantitatively and qualitatively.
- PureseqTM: efficient and accurate prediction of transmembrane topology from amino acid sequence only9
A deep learning framework DeepCNF is proposed that predicts TM topology from amino acid sequence only that outperforms existing sequence-based methods, but also reaches or even surpasses the profile/consensus methods.
- 8
- An examination of handwritten signatures forged using photosensitive signature stamp8
It is demonstrated that a combination of the four analysis methods used in this work can provide a more scientific approach and improve the accuracy and the detection rate of the examination process.
- 7
- Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency7
A novel method to directly achieve accurate white-light colonoscopy image classification by conducting structured cross-modal representation consistency is proposed, realizing multi-modal prediction with a single Transformer while greatly improving the classification accuracy when only with WL images.
- 7
- Facial Peculiarity Retrieval via Deep Neural Networks Fusion7
Facial peculiar features are extracted and classified by dynamically integrated deep neural networks (DNNs), in order to enhance the adaptability in actual conditions and outperforms global feature models in retrieval accuracy.
- 6
- 6
- A Safety Warning Model Based on IAHA-SVM for Coal Mine Environment6
Support vector machine (SVM) parameters are optimized using an improved artificial hummingbird algorithm (IAHA) and its safety level is classified by combining various environmental parameters, and the IAHA-SVM safety warning model is established.
- 6
- 6
- 5
- 5
- Generalize Polyp Segmentation Via Inpainting Across Diverse Backgrounds and Pseudo-Mask Refinement5
This work uses the pre-trained Stable Diffusion Inpaint and ControlNet to introduce a robust generative model capable of inpainting polyps across different backgrounds, and utilizes the prior that synthetic polyps are confined to the inpainted region to establish an inpainted region-guided pseudo-mask refinement network.
- IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models4
This comprehensive assessment highlights each model's strengths and limitations, particularly the outstanding performance of FLUX.1 and Ideogram2.0 in structured and specific domain tasks, underscoring the expanding applications and potential of T2I models as foundational AI tools.
- 4
- A Position Weighted Information Based Word Embedding Model for Machine Translation4
This paper proposes the PW-CBOW word vector model which can present better semantic information in the latest E2E-NMT systems and applies these word vector models on IWSLT14 German-English, WMT14 English-German, W MT14English-French corporas.
- SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training.4
A novel text detection system termed SelfText Beyond Polygon (SBP) with Bounding Box Supervision (BBS) and Dynamic Self Training (DST), where training a polygon-based text detector with only a limited set of upright bounding box annotations is proposed.
- A Novel ELM Ensemble for Time Series Prediction4
This paper presents a novel methodology for time series prediction based on Extreme Learning Machines and an adaptive ensemble techniques that is tested successfully on the CIF 2016 competition datasets which are composed of 72 time series.
- 4
- Characterizing Comprehension of Concurrency Concepts.4
A study is presented through which students’ misconceptions about concurrency and synchronization are identified, categorized their misunderstandings into a misconception pyramid, and subject profiles are built through which the nature and frequency of the misconceptions exhibited by the students are discovered.
- 3
- 3
- MARIO: A Mixed Annotation Framework for Polyp Segmentation3
MARCIO is a mixed supervision model designed to accommodate various annotation types, significantly expanding the range of usable data in polyp segmentation models and highlighting its efficacy in balancing trade-offs between different forms of supervision and maximizing polyp segmentation performance.
- 3
- 3
- 2
- TFNet: point cloud Semantic Segmentation Network based on Triple feature extraction2
TFNet is proposed, an end-to-end deep neural network specifically designed to enhance local geometric feature extraction and improve performance on density variations, which highlights its ability to deliver superior segmentation accuracy and robustness in diverse scenarios.
- MixPolyp: Integrating Mask, Box and Scribble Supervision for Enhanced Polyp Segmentation2
The mixed supervised polyp segmentation paradigm (MixPolyp) combines diverse annotation types (mask, box, and scribble) within a single model, thereby expanding the range of available data and reducing labeling costs.
- 2
- SR-OOD: Out-of-Distribution Detection via Sample Repairing2
This work takes advantage of sample repairing and proposes a novel OOD detection framework, namely SR-OOD, that leverages the idea that repairing an OOD sample can reveal its semantic inconsistency with the in-distribution data.
- 2
- 2
- 2
- 2
- 2
- Tree-Type Irrigation Pipe Network Planning and Design Method Using ICSO-ASV2
The design method proposed in this study can solve the optimal problems of tree-type irrigation pipe networks with varying topologies if essential parameters of the pipe network planning model are provided and the optimal solutions can be generated automatically using the ICSO-ASV algorithm.
- Boost Protein Language Model with Injected Structure Information Through Parameter Efficient Fine-tuning1
Structures Information Injecting Tuning (SI-Tuning) effectively enhances the performance of PLMs by incorporating structural information in a parameter-efficient manner, making it a valuable strategy for applying large-scale PLM to broad biomedical downstream applications.
- 1
- Code and Data Repository for Heuristic Search for Rank Aggregation with Application to Label Ranking1
This paper provides an effective hybrid evolutionary ranking algorithm to solve the rank aggregation problem with both complete and partial rankings, and applies it to label ranking, a well-established machine learning task.
- 1
- 1
- 1
- Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation1
The proposed unsupervised approach to deriving a universal, cross-lingual word embedding space is modeled after domain flow in computer vision, but with a modified objective function and can improve the robustness of adversarial models with comparable and even better precision.
- 1
- Adaptive Residue-wise Profile Fusion for Low Homologous Protein Secondary Structure Prediction Using External Knowledge1
This paper explicitly import external self-supervised knowledge for low homologous PSSP under the guidance of residue-wise profile fusion, which implicitly involves the residue distribution in all native discovered sequences as the complementary features.
- Research on Application of Robot and IOT Technology in Engineering Quality Intelligent Inspection1
The application of robot and IOT in the three-layer of intelligent inspection architecture will promote engineering quality inspection to rapid development of automation and intelligence.
- 1
- Transmembrane Topology Identification by Fusing Evolutionary and Co-evolutionary Information with Cascaded Bidirectional Transformers1
This work proposes a novel approach to identify the transmembrane topology under an object detection framework that takes as the input the predicted 2D distance matrix from the co-evolutionary information, followed by several bidirectional Transformer blocks that effectively fuse both 2D and 1D features for accurate label prediction.
- 1
- An Efficient Graph-Based Flickr Photo Clustering Algorithm1
This paper proposes an efficient Flickr photo clustering algorithm by simultaneous integration information of multiple types which are related to Flickr photos using k-partite graph partitioning.
- 1
- DeepIR-Pred: identification of insulin receptors using metaheuristic optimization of biologically informed multi-view features with deep recurrent learning–
This work proposes a biologically informed deep learning method, DeepIR-Pred, which is the first rigorous model to accurately identify IR proteins, and paves the way for researchers to investigate computational-based methods for IR proteins in depth and unlock new potential in therapeutic discovery.
- MedDATP: Adapting CLIP for few-shot medical image classification via domain adapter and task prompts–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- SEGAN: semi-supervised learning approach for missing data imputation–
This paper theoretically proves that the SEGAN model that introduces a classifier and a missing hint matrix can learn the real known data distribution characteristics when reaching Nash equilibrium.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Machine Learning Classifier Models Can Identify Delirium in Intensive Care Units–
Even with a small number of variables, machine learning has a good ability to predict delirium in critically ill patients, and characteristic variables provide direction for early intervention to reduce the risk ofdelirium.
- –
- Diagnosing Concept Drift in Streaming Data–
A visual analytics method to support model builders and analysts in the identification and correction of concept drift in streaming data, DriftVis, which combines a distribution-based drift detection method with a streaming scatterplot to support the analysis of drift caused by the distribution changes of data streams.
- –
- –
- –
- –
- –
- –
- A study of multi-view gender recognition on a large database–
Experimental results demonstrate that the Pyramid-SVM approach significantly outperforms the traditional SVM classifier, and manages to preserve local information of face images that would otherwise be discarded in the holistic features.
- The Construction on Special Databases of Graduation Quality Education Multimedia WEB–
This paper discusses the principle of constructing databases, body contents, technology requirements about graduation quality education multimedia WEB and the challenges of integrating these into a single system.
- Internet and Science Communication for the Youth–
This dissertation will analyze and summarize the content of the websites of science popularization in combination with discussion over the advantage and purpose of Internet-based science communication.
- The E-mail Pressing Book Returning System Based on Jmail–
Under ILASII 2.0 systematic environment, using ASP combining Jmail package, the pressing book returning system based on E-mail is realized, which would help to improve the management of the library and service level.
- –
- –
- Interface Design of Serial D/A Converter and Single-chip Computer–
The working principle and clock order of serial D/A MAX521, gave connecting way with single-chip computer and some programs.
- Standardization of Digital Reference Service:A Primary Study–
The progress made in standardizing digital reference service and standards such as QuIP,KBIT,QATP, etc are introduced and basic ideas or main contents of these standards are explored, which are useful to the development of standardization ofdigital reference service in China.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.