Research

Selected Talks

• Understanding Post-training through the Lens of Intrinsic Dimension. [Slides]

• Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension. [Slides]

• Toward Fast and Provable Data Selection under Low Intrinsic Dimension. [Slides]

• Robust Blockwise Random Pivoting: Fast and Accurate Adaptive Interpolative Decomposition. [Slides]

• Efficient Bounds and Estimates for Canonical Angles in Randomized Subspace Approximations. [Slides]

Publications

Conference Publications

• Does Weak-to-strong Generalization Happen under Spurious Correlations?
  Chenruo Liu*, Yijun Dong*, Qi Lei.
  ICLR 2026.
  

• Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension.
  Yijun Dong, Yicheng Li, Yunai Li, Jason D. Lee, Qi Lei.
  ICML 2025.
  

• Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining.
  Jianwei Li, Yijun Dong, Qi Lei.
  CPAL 2025.
  

• Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning.
  Yijun Dong*, Hoang Phan*, Xiang Pan*, Qi Lei.
  NeurIPS 2024. [GitHub]
  

• Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering.
  Yijun Dong*, Kevin Miller*, Qi Lei, Rachel Ward.
  NeurIPS 2023. [GitHub]
  

• Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift.
  Yijun Dong*, Yuege Xie*, Rachel Ward.
  ICML 2023. [GitHub]
  

• Sample Efficiency of Data Augmentation Consistency Regularization.
  Shuo Yang*, Yijun Dong*, Rachel Ward, Inderjit Dhillon, Sujay Sanghavi, Qi Lei.
  AISTATS 2023.
  

Journal Publications

• Robust Blockwise Random Pivoting: Fast and Accurate Adaptive Interpolative Decomposition.
  Yijun Dong, Chao Chen, Per-Gunnar Martinsson, Katherine Pearce.
  SIAM Journal on Matrix Analysis and Applications 2025. [GitHub]
  

• Adaptive Parallelizable Algorithms for Interpolative Decompositions via Partially Pivoted LU.
  Katherine J. Pearce, Chao Chen, Yijun Dong, Per-Gunnar Martinsson.
  Numerical Linear Algebra with Applications 2025. [GitHub]
  

• Efficient Bounds and Estimates for Canonical Angles in Randomized Subspace Approximations.
  Yijun Dong, Per-Gunnar Martinsson, Yuji Nakatsukasa.
  SIAM Journal on Matrix Analysis and Applications 2024. [GitHub]
  

• Simpler is better: A comparative study of randomized algorithms for computing the CUR decomposition.
  Yijun Dong, Per-Gunnar Martinsson.
  Advances in Computational Mathematics 2023. [GitHub]
  

• Quantifying Biofilm Formation of Sinorhizobium meliloti Bacterial Strains in Microfluidic Platforms by Measuring the Diffusion Coefficient of Polystyrene Beads.
  Chen Cheng*, Yijun Dong*, Matthew Dorian*, Farhan Kamili*, Effrosyni Seitaridou.
  Open Journal of Biophysics 2017.
  

Preprints & Other Publications

• A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula.
  Chenruo Liu, Yijun Dong, Yiqiu Shen, Qi Lei.
  

• Randomized Time Stepping of Nonlinearly Parametrized Solutions of Evolution Problems.
  Yijun Dong, Paul Schwerdtner, Benjamin Peherstorfer.
  

• Balanced Locality-sensitive Hashing for Online Data Selection.
  Hoang Phan, Yijun Dong, Andrew Gordon Wilson, Qi Lei.
  Optimization for Machine Learning Workshop @ NeurIPS 2025.
  

• Randomly Pivoted V-optimal Design: Fast Data Selection under Low Intrinsic Dimension.
  Yijun Dong*, Xiang Pan*, Hoang Phan*, Qi Lei.
  Workshop on Machine Learning and Compression @ NeurIPS 2024.
  

* denotes equal contribution or alphabetical order. For a complete list of my publications, please visit Google Scholar.