Peng, Liangzu

15 publications

NeurIPS 2025 Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion Qijun Luo, Yifei Shen, Liangzu Peng, Dongsheng Li, Xiao Li

ICLR 2025 LoRanPAC: Low-Rank Random Features and Pre-Trained Models for Bridging Theory and Practice in Continual Learning Liangzu Peng, Juan Elenter, Joshua Agterberg, Alejandro Ribeiro, Rene Vidal

NeurIPS 2025 SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations Buyun Liang, Liangzu Peng, Jinqi Luo, Darshan Thaker, Kwan Ho Ryan Chan, Rene Vidal

ICML 2024 Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares Liangzu Peng, Wotao Yin

CPAL 2024 HARD: Hyperplane ARrangement Descent Tianjiao Ding, Liangzu Peng, Rene Vidal

CVPR 2024 Scalable 3D Registration via Truncated Entry-Wise Absolute Residuals Tianyu Huang, Liangzu Peng, Rene Vidal, Yun-Hui Liu

JMLR 2024 Unlabeled Principal Component Analysis and Matrix Completion Yunzhen Yao, Liangzu Peng, Manolis C. Tsakiris

CVPR 2023 On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation Liangzu Peng, Christian Kümmerle, René Vidal

ICML 2023 The Ideal Continual Learner: An Agent That Never Forgets Liangzu Peng, Paris Giampouras, Rene Vidal

CVPR 2022 ARCS: Accurate Rotation and Correspondence Search Liangzu Peng, Manolis C. Tsakiris, René Vidal

NeurIPS 2022 Global Linear and Local Superlinear Convergence of IRLS for Non-Smooth Robust Regression Liangzu Peng, Christian Kümmerle, Rene Vidal

ECCV 2022 Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search: Tight or Not Liangzu Peng, Mahyar Fazlyab, René Vidal

ICML 2021 Homomorphic Sensing: Sparsity and Noise Liangzu Peng, Boshi Wang, Manolis Tsakiris

NeurIPS 2021 Unlabeled Principal Component Analysis Yunzhen Yao, Liangzu Peng, Manolis Tsakiris

ICML 2019 Homomorphic Sensing Manolis Tsakiris, Liangzu Peng