Huishuai Zhang

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models ACL 2026 De-Anonymization at Scale via Tournament-Style Attribution ACL 2026 AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training EMNLP 2025 Efficient Domain Continual pretraining by Mitigating the Stability Gap ACL 2025 English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025 Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes ICML 2025 ReasVQA: Advancing VideoQA with Imperfect Reasoning Process NAACL 2025 ReMamba: Equip Mamba with Effective Long-Sequence Modeling EMNLP 2025 Understanding Nonlinear Implicit Bias via Region Counts in Input Space ICML 2025 Understanding Visual Detail Hallucinations of Large Vision-Language Models IJCAI 2025 VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format EMNLP 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 NeurIPS 2024 Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks AISTATS 2023 Closing the gap between the upper bound and lower bound of Adam's iteration complexity NeurIPS 2023 Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions COLT 2023 Denoising Masked Autoencoders Help Robust Classification ICLR 2023 DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation NeurIPS 2023 Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping ICLR 2023 FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning NeurIPS 2023 On the Generalization Properties of Diffusion Models NeurIPS 2023 Similarity Distribution Based Membership Inference Attack on Person Re-identification AAAI 2023 Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022 Differentially Private Fine-tuning of Language Models ICLR 2022 Does Momentum Change the Implicit Regularization on Separable Data? NeurIPS 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning ICLR 2021 How Does Data Augmentation Affect Privacy in Machine Learning? AAAI 2021 Large Scale Private Learning via Low-rank Reparametrization ICML 2021 Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD NeurIPS 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 G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space ICLR 2019 SGD Converges to Global Minimum in Deep Learning via Star-convex Path ICLR 2019 On the Local Hessian in Back-propagation NeurIPS 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 NeurIPS 2016 Analysis of Robust PCA via Local Incoherence NeurIPS 2015