Ruoyu Sun

Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives EACL 2026 VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision ACL 2026 Adam-mini: Use Fewer Learning Rates To Gain More ICLR 2025 A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality EMNLP 2025 Preserving Diversity in Supervised Fine-Tuning of Large Language Models ICLR 2025 Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion ACL 2025 Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming ICLR 2025 When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach ICLR 2025 AceGPT, Localizing Large Language Models in Arabic NAACL 2024 Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization COLT 2024 Empower Programmable Pipeline for Advanced Stateful Packet Processing NSDI 2024 FinBPM: A Framework for Portfolio Management-based Financial Investor Behavior Perception Model EACL 2024 How Graph Neural Networks Learn: Lessons from Training Dynamics ICML 2024 LEMON: Lossless model expansion ICLR 2024 On the Power of Small-size Graph Neural Networks for Linear Programming NeurIPS 2024 PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming ICML 2024 ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models ICML 2024 SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization NeurIPS 2024 Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization EMNLP 2024 Why Transformers Need Adam: A Hessian Perspective NeurIPS 2024 A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming ICLR 2023 Balanced Training for Sparse GANs NeurIPS 2023 NTK-SAP: Improving neural network pruning by aligning training dynamics ICLR 2023 PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization NeurIPS 2023 Adam Can Converge Without Any Modification On Update Rules NeurIPS 2022 DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data NeurIPS 2022 Does Momentum Change the Implicit Regularization on Separable Data? NeurIPS 2022 Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning CVPR 2022 Stability Analysis and Generalization Bounds of Adversarial Training NeurIPS 2022 Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data NeurIPS 2021 PenDer: Incorporating Shape Constraints via Penalized Derivatives AAAI 2021 RMSprop converges with proper hyper-parameter ICLR 2021 When Expressivity Meets Trainability: Fewer than n Neurons Can Work NeurIPS 2021 A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems NeurIPS 2020 Towards a Better Global Loss Landscape of GANs NeurIPS 2020 Max-Sliced Wasserstein Distance and Its Use for GANs CVPR 2019 On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization ICLR 2019 Adding One Neuron Can Eliminate All Bad Local Minima NeurIPS 2018 Understanding the Loss Surface of Neural Networks for Binary Classification ICML 2018 Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems NeurIPS 2015