← Authors

Huishuai Zhang

40 papers · 2015–2025 · 12 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (10) πŸ—ΊοΈ Taxonomy Completionist (63) 🌍 Conference Polyglot (12) 🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (13) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (13) 🧬 Topic Evolution πŸš€ Conference Pioneer ⚑ Prolific Year (9) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (151) πŸ’Ž Century Club (40) πŸ”₯ Unstoppable (11)

Conferences

NIPS (10) ICML (7) ICLR (6) EMNLP (5) AAAI (3) IJCAI (3) ACL (1) AISTATS (1) COLT (1) CVPR (1) JMLR (1) NAACL (1)

Top co-authors

Wei Chen (13) Tie-yan Liu (11) Dongyan Zhao (9) Da Yu (8) Bohan Wang (5) Yingbin Liang (5) Qi Meng (4) Di He (4) Yueqian Wang (3) Zhi-ming Ma (3)

Research topics

Privacy (2) Differential Privacy (1)

Keywords

neural network (5) generalization bound (4) gradient descent (4) phase retrieval (3) wirtinger flow (3) gradient perturbation (2) privacy risk (2) large language model (2) privacy attack (2) learning rate (2) stochastic gradient descent (2) adversarial example (2) membership inference (2) membership inference attack (2) non-convex optimization (2) neural network optimization (2) differential privacy (2) batch normalization (2) few-shot learning (2) convex optimization (2)

Papers

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process NAACL 2025
Efficient Domain Continual pretraining by Mitigating the Stability Gap ACL 2025
AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training EMNLP 2025
English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025
VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format EMNLP 2025
ReMamba: Equip Mamba with Effective Long-Sequence Modeling EMNLP 2025
Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes ICML 2025
Understanding Nonlinear Implicit Bias via Region Counts in Input Space ICML 2025
Understanding Visual Detail Hallucinations of Large Vision-Language Models IJCAI 2025
Differentially Private Synthetic Data via Foundation Model APIs 2: Text ICML 2024
Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules EMNLP 2024
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token NIPS 2024
Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions COLT 2023
DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation NIPS 2023
Similarity Distribution Based Membership Inference Attack on Person Re-identification AAAI 2023
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks AISTATS 2023
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping ICLR 2023
Denoising Masked Autoencoders Help Robust Classification ICLR 2023
On the Generalization Properties of Diffusion Models NIPS 2023
Closing the gap between the upper bound and lower bound of Adam's iteration complexity NIPS 2023
FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning NIPS 2023
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022
Differentially Private Fine-tuning of Language Models ICLR 2022
Does Momentum Change the Implicit Regularization on Separable Data? NIPS 2022
Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD NIPS 2021
Large Scale Private Learning via Low-rank Reparametrization ICML 2021
How Does Data Augmentation Affect Privacy in Machine Learning? AAAI 2021
Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning ICLR 2021
Gradient Perturbation is Underrated for Differentially Private Convex Optimization IJCAI 2020
On Layer Normalization in the Transformer Architecture ICML 2020
BN-invariant Sharpness Regularizes the Training Model to Better Generalization IJCAI 2019
Capacity Control of ReLU Neural Networks by Basis-Path Norm AAAI 2019
SGD Converges to Global Minimum in Deep Learning via Star-convex Path ICLR 2019
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space ICLR 2019
On the Local Hessian in Back-propagation NIPS 2018
A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms JMLR 2017
Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow ICML 2016
Reshaped Wirtinger Flow for Solving Quadratic System of Equations NIPS 2016
Analysis of Robust PCA via Local Incoherence NIPS 2015