Zhongyuan Wang
14 papers · 0 citations
Most-cited papers
- Multi-scale Progressive Fusion Network For Single Image Deraining2020 · 679 citations
- Hit: Hierarchical Transformer With Momentum Contrast For Video-text Retrieval2021 · 134 citations
- Degrade Is Upgrade: Learning Degradation For Low-light Image Enhancement2021 · 44 citations
- Towards Practical Capture Of High-fidelity Relightable Avatars2023 · 24 citations
- Rap: Redundancy-aware Video-language Pre-training For Text-video Retrieval2022 · 4 citations
- Omnigen2: Towards Instruction-aligned Multimodal Generation2025
- Omnigen2: Towards Instruction-aligned Multimodal Generation2025
- Emu3.5: Native Multimodal Models Are World Learners2025
- Ac-dit: Adaptive Coordination Diffusion Transformer For Mobile Manipulation2025
- Mathsticks: A Benchmark For Visual Symbolic Compositional Reasoning With Matchstick Puzzles2025
- End-to-end Training Of Multimodal Model And Ranking Model2024
- Tiger: Tool-integrated Geometric Reasoning In Vision-language Models For Robotics2025
- Sapave: Towards Active Perception And Manipulation In Vision-language-action Models For Robotics2026
- Tokenflow: Rethinking Fine-grained Cross-modal Alignment In Vision-language Retrieval2022
Topics