Siyuan Li

Orcid: 0000-0001-6806-2468

Affiliations:
  • Westlake University, School of Engineering, Hangzhou, China
  • Alibaba Group (China), Hangzhou, China (former)
  • Nanjing University, Department of Computer Science and Technology, China (former)


According to our database1, Siyuan Li authored at least 73 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Discovering the Representation Bottleneck of Graph Neural Networks.
IEEE Trans. Knowl. Data Eng., December, 2024

Enhancing human-like multimodal reasoning: a new challenging dataset and comprehensive framework.
Neural Comput. Appl., November, 2024

GNN Cleaner: Label Cleaner for Graph Structured Data.
IEEE Trans. Knowl. Data Eng., February, 2024

MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction.
CoRR, 2024

TopoFR: A Closer Look at Topology Alignment on Face Recognition.
CoRR, 2024

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning.
CoRR, 2024

A Survey on Mixup Augmentations and Beyond.
CoRR, 2024

CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph.
CoRR, 2024

Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions.
CoRR, 2024

GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models.
CoRR, 2024

Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning.
CoRR, 2024

UniIF: Unified Molecule Inverse Folding.
CoRR, 2024

Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning.
CoRR, 2024

Switch EMA: A Free Lunch for Better Flatness and Sharpness.
CoRR, 2024

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond.
CoRR, 2024

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

MogaNet: Multi-order Gated Aggregation Network.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

SemiReward: A General Reward Model for Semi-supervised Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-consistency Training.
Proceedings of the Computer Vision - ECCV 2024, 2024

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Wavelet-Driven Spatiotemporal Predictive Learning: Bridging Frequency and Time Variations.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
MMDesign: Multi-Modality Transfer Learning for Generative Protein Design.
CoRR, 2023

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training.
CoRR, 2023

Protein 3D Graph Structure Learning for Robust Structure-based Protein Property Prediction.
CoRR, 2023

Revisiting the Temporal Modeling in Spatio-Temporal Predictive Learning under A Unified View.
CoRR, 2023

Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework.
CoRR, 2023

Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration.
CoRR, 2023

InstructBio: A Large-scale Semi-supervised Learning Paradigm for Biochemical Problems.
CoRR, 2023

Lightweight Contrastive Protein Structure-Sequence Transformation.
CoRR, 2023

Explaining Graph Neural Networks via Non-parametric Subgraph Matching.
CoRR, 2023

Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Harnessing Hard Mixed Samples with Decoupled Regularizer.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching.
Proceedings of the International Conference on Machine Learning, 2023

Architecture-Agnostic Masked Image Modeling - From ViT back to CNN.
Proceedings of the International Conference on Machine Learning, 2023

Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Deep manifold embedding of attributed graphs.
Neurocomputing, 2022

Non-equispaced Fourier Neural Solvers for PDEs.
CoRR, 2022

Efficient Multi-order Gated Aggregation Network.
CoRR, 2022

Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation.
CoRR, 2022

OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning.
CoRR, 2022

UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection.
CoRR, 2022

DLME: Deep Local-flatness Manifold Embedding.
CoRR, 2022

Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning.
CoRR, 2022

Architecture-Agnostic Masked Image Modeling - From ViT back to CNN.
CoRR, 2022

Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions.
CoRR, 2022

neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning.
CoRR, 2022

Decoupled Mixup for Data-efficient Learning.
CoRR, 2022

Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

DLME: Deep Local-Flatness Manifold Embedding.
Proceedings of the Computer Vision - ECCV 2022, 2022

AutoMix: Unveiling the Power of Mixup for Stronger Classifiers.
Proceedings of the Computer Vision, 2022

Hyperspherical Consistency Regularization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Are Gradients on Graph Structure Reliable in Gray-box Attacks?
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

Exploring Localization for Self-supervised Fine-grained Contrastive Learning.
Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup.
CoRR, 2021

GenURL: A General Framework for Unsupervised Representation Learning.
CoRR, 2021

Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment.
CoRR, 2021

Unsupervised Deep Manifold Attributed Graph Embedding.
CoRR, 2021

AutoMix: Unveiling the Power of Mixup.
CoRR, 2021

Invertible Manifold Learning for Dimension Reduction.
Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2021

2020
Deep Clustering and Representation Learning that Preserves Geometric Structures.
CoRR, 2020

TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020


  Loading...