Wenhai Wang

59 papers · 2018–2026 · 11 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (11) 🏃 Academic Marathon (7) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (69) 🔬 Deep Specialist (16) 🧬 Topic Evolution 👥 Mega-Team (38) 👑 Triple Crown 🤝 Dynamic Duo (28) 🏆 Grand Slam 💎 Century Club (58) 🔥 Unstoppable (8) 📈 Trend Setter 🗃️ Keyword Collector (209) ⚡ Prolific Year (9)

Conferences

CVPR (13) NIPS (10) ECCV (9) ICCV (6) AAAI (5) ICLR (5) IJCAI (4) ICML (3) ACL (2) EMNLP (1) NAACL (1)

Top co-authors

Jifeng Dai (28) Yu Qiao (24) Tong Lu (20) Xizhou Zhu (19) Zhe Chen (18) Ping Luo (16) Lewei Lu (14) Enze Xie (14) Weiyun Wang (9) hongsheng Li (7)

Research topics

Optimization & Theory (1)

Keywords

semantic segmentation (10) vision-language model (8) object detection (7) multimodal large language model (5) convolutional neural network (5) multi-modal learning (4) multimodal learning (4) foundation model (3) image generation (3) multi-task learning (3) vision transformer (3) instance segmentation (3) visual question answering (3) zero-shot learning (2) diffusion model (2) feature fusion (2) scene text detection (2) image segmentation (2) deformable convolution (2) contrastive learning (2)

Papers

EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models AAAI 2026

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework ICCV 2025

HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding CVPR 2025

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models CVPR 2025

Docopilot: Improving Multimodal Models for Document-Level Understanding CVPR 2025

CoMemo: LVLMs Need Image Context with Image Memory ICML 2025

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures ICLR 2025

UltraModel: A Modeling Paradigm for Industrial Objects IJCAI 2025

Diffuse&Refine: Intrinsic Knowledge Generation and Aggregation for Incremental Object Detection IJCAI 2025

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text ICLR 2025

MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost ICML 2025

ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area AAAI 2025

Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting AAAI 2025

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference ACL 2025

Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction ICCV 2025

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning NIPS 2024

Needle In A Multimodal Haystack NIPS 2024

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD NIPS 2024

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks NIPS 2024

AVSegFormer: Audio-Visual Segmentation with Transformer AAAI 2024

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks CVPR 2024

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications CVPR 2024

ControlLLM: Augment Language Models with Tools by Searching on Graphs ECCV 2024

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World ECCV 2024

Distilling Knowledge from Large-Scale Image Models for Object Detection ECCV 2024

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments ICLR 2024

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World ICLR 2024

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis ICML 2024

Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization NAACL 2024

InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions CVPR 2023

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks NIPS 2023

FB-BEV: BEV Representation from Forward-Backward View Transformations ICCV 2023

Planning-Oriented Autonomous Driving CVPR 2023

Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks CVPR 2023

Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection NIPS 2023

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought NIPS 2023

Vision Transformer Adapter for Dense Predictions ICLR 2023

CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Code EMNLP 2023

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization AAAI 2022

VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition ECCV 2022

Panoptic SegFormer: Delving Deeper Into Panoptic Segmentation With Transformers CVPR 2022

Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs NIPS 2022

BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers ECCV 2022

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers NIPS 2021

Segmenting Transparent Objects in the Wild with Transformer IJCAI 2021

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection CVPR 2021

DetCo: Unsupervised Contrastive Learning for Object Detection ICCV 2021

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions ICCV 2021

Scene Text Image Super-resolution in the wild ECCV 2020

Segmenting Transparent Objects in the Wild ECCV 2020

AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting ECCV 2020

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection NIPS 2020

PolarMask: Single Shot Instance Segmentation With Polar Representation CVPR 2020

Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation ECCV 2020

Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network ICCV 2019

Selective Kernel Networks CVPR 2019

Shape Robust Text Detection With Progressive Scale Expansion Network CVPR 2019

Mixed Link Networks IJCAI 2018