Yuwei Wu

45 papers · 2017–2026 · 11 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🏃 Academic Marathon (8) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (11) 🐝 Cross-Pollinator (6)

🐝 Cross-Pollinator (6) 🌈 Renaissance Researcher (10) 🗺️ Taxonomy Completionist (105) 🏆 Grand Slam 🏆 Keyword Champion (2) 🤝 Dynamic Duo (30) 🗃️ Keyword Collector (224) 💎 Century Club (43) 🔥 Unstoppable (7) ⚡ Prolific Year (7)

Conferences

AAAI (14) CVPR (13) ICCV (5) ECCV (3) NIPS (3) IJCAI (2) EMNLP (1) ICLR (1) ICML (1) NAACL (1) RSS (1)

Top co-authors

Yunde Jia (32) Zhi Gao (10) Chenchen Jing (9) Mehrtash Harandi (8) Chuanhao Li (8) Zhen Li (7) Chengtang Yao (5) Che Sun (5) Mingliang Zhai (4) Weixiao Liu (4)

Keywords

visual question answering (8) compositional generalization (5) stereo matching (3) riemannian optimization (3) machine reading comprehension (3) 3d reconstruction (3) hyperbolic space (3) graph neural network (3) point cloud (3) manifold optimization (2) few-shot learning (2) 3d vision (2) manifold learning (2) reinforcement learning (2) metric learning (2) video anomaly detection (2) multimodal learning (2) continual learning (2) disparity estimation (2) self-supervised learning (2)

Papers

Composition-Incremental Learning for Compositional Generalization AAAI 2026 LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images AAAI 2026 Diving into the Fusion of Monocular Priors for Generalized Stereo Matching ICCV 2025 Large Language Models are Demonstration Pre-Selectors for Themselves ICML 2025 Consistency of Compositional Generalization Across Multiple Levels AAAI 2025 Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage ICLR 2025 Multi-Sourced Compositional Generalization in Visual Question Answering IJCAI 2025 World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving AAAI 2025 Temporally Consistent Stereo Matching ECCV 2024 SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge NIPS 2024 FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models NIPS 2024 Residual Hyperbolic Graph Convolution Networks AAAI 2024 In-Context Compositional Generalization for Large Vision-Language Models EMNLP 2024 Compositional Substitutivity of Visual Reasoning for Visual Question Answering ECCV 2024 Learning Event-Relevant Factors for Video Anomaly Detection AAAI 2023 Exploring Data Geometry for Continual Learning CVPR 2023 Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language CVPR 2023 Marching-Primitives: Shape Abstraction From Signed Distance Function CVPR 2023 Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding IJCAI 2023 Learning-Free Grasping of Unknown Objects Using Hidden Superquadrics RSS 2023 Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks ICCV 2023 Parameterized Cost Volume for Stereo Matching ICCV 2023 Sparse Point Guided 3D Lane Detection ICCV 2023 Global-Aware Registration of Less-Overlap RGB-D Scans CVPR 2022 Learning the Dynamics of Visual Relational Reasoning via Reinforced Path Routing AAAI 2022 Efficient Riemannian Meta-Optimization by Implicit Differentiation AAAI 2022 Robust and Accurate Superquadric Recovery: A Probabilistic Approach CVPR 2022 Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds NIPS 2022 Primitive3D: 3D Object Dataset Synthesis From Randomly Assembled Primitives CVPR 2022 Maintaining Reasoning Consistency in Compositional Visual Question Answering CVPR 2022 Primitive-Based Shape Abstraction via Nonparametric Bayesian Inference ECCV 2022 A Hyperbolic-to-Hyperbolic Graph Convolutional Network CVPR 2021 Curvature Generation in Curved Spaces for Few-Shot Learning ICCV 2021 A Decomposition Model for Stereo Matching CVPR 2021 Learning a Gradient-free Riemannian Optimizer on Tangent Spaces AAAI 2021 Personalized Response Generation via Generative Split Memory Network NAACL 2021 On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks CVPR 2020 Semantics-Aware BERT for Language Understanding AAAI 2020 Learning to Optimize on SPD Manifolds CVPR 2020 DCMN+: Dual Co-Matching Network for Multi-Choice Reading Comprehension AAAI 2020 Overcoming Language Priors in VQA via Decomposed Linguistic Representations AAAI 2020 SG-Net: Syntax-Guided Machine Reading Comprehension AAAI 2020 Revisiting Bilinear Pooling: A Coding Perspective AAAI 2020 3D Shape Reconstruction From Images in the Frequency Domain CVPR 2019 HOPE: Hierarchical Object Prototype Encoding for Efficient Object Instance Search in Videos CVPR 2017