Kun Yuan

Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion AAAI 2026 Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures ICLR 2025 Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance ICML 2025 Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition MICCAI 2025 A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models ICML 2025 KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception CVPR 2025 Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity JMLR 2025 Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration JMLR 2025 ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment EMNLP 2025 Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold ICML 2025 Visual Autoregressive Modeling for Image Super-Resolution ICML 2025 Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks ICML 2025 OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining ICCV 2025 Subspace Optimization for Large Language Models with Convergence Guarantees ICML 2025 EndoVLA: Dual-Phase Vision-Language-Action for Precise Autonomous Tracking in Endoscopy CORL 2025 Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment AAAI 2025 HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference ACL 2025 Optimal Complexity in Byzantine-Robust Distributed Stochastic Optimization with Data Heterogeneity JMLR 2025 SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting MICCAI 2025 Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement MICCAI 2025 MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments CVPR 2025 HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition MICCAI 2024 Distributed Bilevel Optimization with Communication Compression ICML 2024 SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization NIPS 2024 Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation NIPS 2024 XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution ECCV 2024 Momentum Benefits Non-iid Federated Learning Simply and Provably ICLR 2024 PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild CVPR 2024 Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model MICCAI 2024 KVQ: Kwai Video Quality Assessment for Short-form Videos CVPR 2024 DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm ICML 2023 Unbiased Compression Saves Communication in Distributed Optimization: When and How Much? NIPS 2023 Quality-Aware Pre-Trained Models for Blind Image Quality Assessment CVPR 2023 BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection CVPR 2023 AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation ICML 2023 Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD JMLR 2023 Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization NIPS 2022 Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression NIPS 2022 Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate NIPS 2022 Effective Model Sparsification by Scheduled Grow-and-Prune Methods ICLR 2022 CHEX: CHannel EXploration for CNN Model Compression CVPR 2022 Self-Supervised Correlation Mining Network for Person Image Generation CVPR 2022 Exponential Graph is Provably Efficient for Decentralized Deep Training NIPS 2021 Accelerating Gossip SGD with Periodic Global Averaging ICML 2021 An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders NIPS 2021 Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch ICLR 2021 DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training ICCV 2021 Incorporating Convolution Designs Into Visual Transformers ICCV 2021 Differentiable Dynamic Wirings for Neural Networks ICCV 2021 Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation ECCV 2020 Learning Connectivity of Neural Networks from a Topological Perspective ECCV 2020 A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization NIPS 2019 SafeNet: Scale-normalization and Anchor-based Feature Extraction Network for Person Re-identification IJCAI 2018 On the Influence of Momentum Acceleration on Online Learning JMLR 2016