Zhanxing Zhu

40 papers · 2015–2026 · 8 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🌍 Conference Polyglot (8) 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (10)

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (10) 👑 Triple Crown 🏆 Grand Slam 🔬 Deep Specialist (11) 🏆 Keyword Champion (2) 📈 Trend Setter 🚀 Conference Pioneer 🗃️ Keyword Collector (153) ⚡ Prolific Year (5) 💎 Century Club (39) 🔥 Unstoppable (9)

Conferences

NIPS (12) ICML (8) AAAI (7) ICLR (6) ACML (2) CVPR (2) IJCAI (2) ACL (1)

Top co-authors

Nanyang Ye (5) Dinghuai Zhang (4) Bochen Lyu (4) Bing Yu (4) Jingfeng Wu (3) Zhouchen Lin (3) Ke Sun (3) Qianxiao Li (2) Jinwen Ma (2) Tianyuan Zhang (2)

Research topics

Optimization (1)

Keywords

adversarial training (6) stochastic gradient descent (5) markov chain monte carlo (3) langevin dynamics (3) adversarial attack (3) semi-supervised learning (3) stochastic optimization (3) bayesian inference (3) convolutional neural network (2) stochastic gradient (2) adversarial perturbation (2) hamiltonian monte carlo (2) computational efficiency (2) deep learning (2) neural architecture search (2) representation learning (2) domain generalization (2) virtual adversarial training (2) posterior distribution (2) implicit bia (2)

Papers

ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction AAAI 2026 Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems ICML 2025 A Solvable Attention for Neural Scaling Laws ICLR 2025 DyCAST: Learning Dynamic Causal Structure from Time Series ICLR 2025 Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks AAAI 2025 Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization NIPS 2024 Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy ACML 2023 Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling NIPS 2023 Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network NIPS 2023 MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows ICML 2023 Implicit Bias of Adversarial Training for Deep Neural Networks ICLR 2022 Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics ICLR 2022 Adversarial Invariant Learning CVPR 2021 AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models ICLR 2021 Neural Approximate Sufficient Statistics for Implicit Models ICLR 2021 Amata: An Annealing Mechanism for Adversarial Training Acceleration AAAI 2021 Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization ICML 2021 Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay NIPS 2021 Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting AAAI 2021 Informative Dropout for Robust Representation Learning: A Shape-bias Perspective ICML 2020 On the Noisy Gradient Descent that Generalizes as SGD ICML 2020 Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes AAAI 2020 Efficient Neural Architecture Search via Proximal Iterations AAAI 2020 Towards Understanding and Improving the Transferability of Adversarial Examples in Deep Neural Networks ACML 2020 Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher NIPS 2020 Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework NIPS 2020 On Breaking Deep Generative Model-based Defenses and Beyond ICML 2020 The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects ICML 2019 SpHMC: Spectral Hamiltonian Monte Carlo AAAI 2019 Interpreting Adversarially Trained Convolutional Neural Networks ICML 2019 Tangent-Normal Adversarial Regularization for Semi-Supervised Learning CVPR 2019 You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle NIPS 2019 Stochastic Fractional Hamiltonian Monte Carlo IJCAI 2018 Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning NIPS 2018 Reinforced Continual Learning NIPS 2018 Bayesian Adversarial Learning NIPS 2018 Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting IJCAI 2018 Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks NIPS 2017 Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix ACL 2017 Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling NIPS 2015