Weizhong Zhang

Advanced Black-Box Tuning of Large Language Models with Limited API Calls AAAI 2026 Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training AAAI 2026 Investigating Data Pruning for Pretraining Biological Foundation Models at Scale AAAI 2026 Achieving Ensemble-Like Performance in a Single Model: A Feature Diversification Framework for Image-Text Matching AAAI 2025 Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient ACL 2025 DreamText: High Fidelity Scene Text Synthesis CVPR 2025 Expanding the Scope of Negatives: Boosting Image-Text Matching with Negatives Distribution Guided Learning AAAI 2025 Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Population Normalization for Federated Learning CVPR 2025 TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data NAACL 2025 Towards Robust Influence Functions with Flat Validation Minima ICML 2025 Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost ICLR 2024 Efficient Denoising Diffusion via Probabilistic Masking ICML 2024 FusionFormer: A Concise Unified Feature Fusion Transformer for 3D Pose Estimation AAAI 2024 High-fidelity Person-centric Subject-to-Image Synthesis CVPR 2024 Low Precision Local Training is Enough for Federated Learning NeurIPS 2024 Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection AAAI 2024 PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization CVPR 2024 Spurious Feature Diversification Improves Out-of-distribution Generalization ICLR 2024 A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond ICLR 2023 DynaFed: Tackling Client Data Heterogeneity With Global Dynamics CVPR 2023 DynaMS: Dyanmic Margin Selection for Efficient Deep Learning ICLR 2023 Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning ICLR 2023 Finding Dynamics Preserving Adversarial Winning Tickets AISTATS 2022 Model Agnostic Sample Reweighting for Out-of-Distribution Learning ICML 2022 Probabilistic Bilevel Coreset Selection ICML 2022 Sparse Invariant Risk Minimization ICML 2022 Effective Sparsification of Neural Networks With Global Sparsity Constraint CVPR 2021 Efficient Neural Network Training via Forward and Backward Propagation Sparsification NeurIPS 2021 Gradient Method for Continuous Influence Maximization with Budget-Saving Considerations AAAI 2020 How to Characterize The Landscape of Overparameterized Convolutional Neural Networks NeurIPS 2020 A Sufficient Condition for Convergences of Adam and RMSProp CVPR 2019 Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction JMLR 2019 Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning NeurIPS 2018 Safe Element Screening for Submodular Function Minimization ICML 2018 Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction ICML 2017