James Kwok

DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs CVPR 2026 Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting AAAI 2026 Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning EMNLP 2025 Curriculum-aware Training for Discriminating Molecular Property Prediction Models ICLR 2025 End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation EMNLP 2025 Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization ICLR 2025 Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment ACL 2025 Nested-Refinement Metamorphosis: Reflective Evolution for Efficient Optimization of Networking Problems ACL 2025 Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction ICML 2025 Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging ICML 2025 Efficient Pareto Manifold Learning with Low-Rank Structure ICML 2024 "Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation" ECCV 2024 Forward-Backward Reasoning in Large Language Models for Mathematical Verification ACL 2024 Implicit Concept Removal of Diffusion Models ECCV 2024 Improving Sharpness-Aware Minimization by Lookahead ICML 2024 Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy ECCV 2024 MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models ICLR 2024 Multi-Resolution Diffusion Models for Time Series Forecasting ICLR 2024 PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis ICLR 2024 An Adaptive Policy to Employ Sharpness-Aware Minimization ICLR 2023 Effective Structured Prompting by Meta-Learning and Representative Verbalizer ICML 2023 Enhancing Meta Learning via Multi-Objective Soft Improvement Functions ICLR 2023 GrowCLIP: Data-Aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-Training ICCV 2023 KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion EMNLP 2023 Leveraging per Image-Token Consistency for Vision-Language Pre-Training CVPR 2023 Non-autoregressive Conditional Diffusion Models for Time Series Prediction ICML 2023 Nonparametric Iterative Machine Teaching ICML 2023 Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts ICLR 2023 Efficient Variance Reduction for Meta-learning ICML 2022 Revisiting Over-smoothing in BERT from the Perspective of Graph ICLR 2022 Subspace Learning for Effective Meta-Learning ICML 2022 Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback NeurIPS 2019 Normalization Helps Training of Quantized LSTM NeurIPS 2019 Privacy-Preserving Stacking with Application to Cross-organizational Diabetes Prediction IJCAI 2019 Scalable Robust Matrix Factorization with Nonconvex Loss NeurIPS 2018 Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity ICML 2016 Fast Second Order Stochastic Backpropagation for Variational Inference NeurIPS 2015 Accelerated Stochastic Gradient Method for Composite Regularization AISTATS 2014 Asynchronous Distributed ADMM for Consensus Optimization ICML 2014 Fast Stochastic Alternating Direction Method of Multipliers ICML 2014 Covariate Shift in Hilbert Space: A Solution via Sorrogate Kernels ICML 2013 Efficient Multi-label Classification with Many Labels ICML 2013