Chun Yuan

M3Time: LLM-Enhanced Multi-Modal, Multi-Scale, and Multi-Frequency Multivariate Time Series Forecasting AAAI 2026 Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation AAAI 2026 PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering ACL 2026 A-ADAPT: Adaptive Intracranial Artery Segmentation with Morphology-Guided Prompts and Difficulty-Aware Learning MIDL 2026 Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models CVPR 2025 LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs CVPR 2025 ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices CVPR 2025 ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning ICCV 2025 Aligning Composed Query with Image via Discriminative Perception from Negative Correspondences AAAI 2025 IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis AAAI 2025 Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction AAAI 2025 Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent ICML 2025 FlatQuant: Flatness Matters for LLM Quantization ICML 2025 Preference Optimization for Combinatorial Optimization Problems ICML 2025 Unsupervised Domain Adaptive Visual Question Answering in the Era of Multi-Modal Large Language Models WACV 2025 Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss ICML 2025 Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors ICML 2025 ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding ICLR 2025 Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation ICLR 2025 IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning ICLR 2025 VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition ICCV 2025 Text-guided Visual Prompt DINO for Generic Segmentation ICCV 2025 Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models ICCV 2025 SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling ICCV 2025 UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis ICCV 2025 Edge-Aware Hierarchical Graph Transformer to Decode Brain Arterial Network MICCAI 2025 CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers ICML 2024 SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition NIPS 2024 Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery AAAI 2024 Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework AAAI 2024 Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution AAAI 2024 Deep Homography Estimation for Visual Place Recognition AAAI 2024 IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact ACL 2024 FREE: Faster and Better Data-Free Meta-Learning CVPR 2024 Distilling Semantic Priors from SAM to Efficient Image Restoration Models CVPR 2024 CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition CVPR 2024 GVGEN: Text-to-3D Generation with Volumetric Representation ECCV 2024 DreamDiffusion: High-Quality EEG-to-Image Generation with Temporal Masked Signal Modeling and CLIP Alignment ECCV 2024 A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting ECCV 2024 MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections ECCV 2024 Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition ICLR 2024 Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model ICLR 2024 Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications ICML 2024 DFD: Distilling the Feature Disparity Differently for Detectors ICML 2024 Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models ICML 2024 DFVSR: Directional Frequency Video Super-Resolution via Asymmetric and Enhancement Alignment Network IJCAI 2023 MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy NIPS 2023 Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding ICCV 2023 Why Is the Winner the Best? CVPR 2023 Tailoring Instructions to Student’s Learning Levels Boosts Knowledge Distillation ACL 2023 LET: Leveraging Error Type Information for Grammatical Error Correction ACL 2023 Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning CVPR 2023 High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors CVPR 2023 Learning Imbalanced Data With Vision Transformers CVPR 2023 Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks CVPR 2023 When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method ICCV 2023 Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos AAAI 2023 HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details ICCV 2023 Accurate 3D Face Reconstruction with Facial Component Tokens ICCV 2023 From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels ICCV 2023 Darwinian Model Upgrades: Model Evolving with Selective Compatibility AAAI 2023 Learning to Learn from APIs: Black-Box Data-Free Meta-Learning ICML 2023 UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers ICML 2023 Diverse Image Inpainting with Normalizing Flow ECCV 2022 Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization ECCV 2022 Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval ICLR 2022 SWEM: Towards Real-Time Video Object Segmentation With Sequential Weighted Expectation-Maximization CVPR 2022 Focal and Global Knowledge Distillation for Detectors CVPR 2022 One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations NIPS 2022 Structural Supervision for Word Alignment and Machine Translation ACL 2022 Towards Universal Backward-Compatible Representation Learning IJCAI 2022 REALY: Rethinking the Evaluation of 3D Face Reconstruction ECCV 2022 Masked Generative Distillation ECCV 2022 Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images ECCV 2022 Cross-modal Representation Learning and Relation Reasoning for Bidirectional Adaptive Manipulation IJCAI 2022 Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective NIPS 2021 Reducing the Annotation Effort for Video Object Segmentation Datasets WACV 2021 Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition CVPR 2020 Feature Augmented Memory with Global Attention Network for VideoQA IJCAI 2020 Self-Attention ConvLSTM for Spatiotemporal Prediction AAAI 2020 Bridge the Gap: High-level Semantic Planning for Image Captioning COLING 2020 HAF-SVG: Hierarchical Stochastic Video Generation with Aligned Features IJCAI 2020 Self-Supervised Mixture-of-Experts by Uncertainty Estimation AAAI 2019 Multi-Scale Visual Semantics Aggregation with Self-Attention for End-to-End Image-Text Matching ACML 2019 Self-Adaptive Double Bootstrapped DDPG IJCAI 2018 TreeNet: Learning Sentence Representations with Unconstrained Tree Structure IJCAI 2018