Embodied intelligence
Exploring a hierarchical architecture with an agent planner and either a native-action agent or a VLA model, connecting task planning, action execution and environment feedback.
Research enquiriesMultimodal intelligence
Understanding and generating content across vision and language, including images, videos and human motion.
Related outputsAI for Science (AI4S)
Developing AI methods for biomolecular prediction and design, virus evolution, protein structure and medical image analysis.
Related outputsResearch outputs
Explore our work by title, author, keyword, year or research area.
124 research outputs · 2010–2026
2026
23 outputsUnified Granularity Controller for Interactive Segmentation
Switch-UMamba: Dynamic scanning vision Mamba UNet for medical image segmentation
DemoChain: Decoupled Motion-Chain for Multi-Action Video Generation
Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search
Antibody-antigen neutralization prediction by integrating structural information distillation and physicochemical constraints
Zero-shot Benchmarking of RNA Language Models in Structural, Functional, and Evolutionary Learning
WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation
ControlPose: High-Fidelity Pose-Controlled Image Generation with Multi-Faceted Pose Disentanglement
Divergent Thinking: Escape the Homogeneity Trap in Generative Commonsense Reasoning
Comp-Attn: Present-and-Align Attention for Compositional Video Generation
BioDynaSpec: Harmonic-Guided Spatio-Spectral Autoregressive Diffusion for Protein Dynamics Generation
RealDyadic: Synthesizing Realistic Dyadic 3D Dialogue with Neural Appearance Priors
Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration
UI2V-Bench: An Understanding-Driven Image-to-video Generation Benchmark
2025
16 outputsAligning Instance Brownian Bridge with Texts for Open-vocabulary Video Instance Segmentation
A Unified Peptide Generative Framework via a Weakly Order-Dependent Autoregressive Language Model and Lifelong Learning
Oriented-derivative Representation for Boundary-aware Polyp Segmentation
Predicting protein stability changes upon mutations with dual-view ensemble learning from single sequence
Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution
RetinaStereo: Dynamic-Volume Stereo Matching Network
iSegMan: Interactive Segment-and-Manipulate 3D Gaussians
Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting
Temporal-aware Query Routing for Real-time Video Instance Segmentation
Referent-aligned Training for Unsupervised Interactive Segmentation
2024
19 outputsDual-Level Masked Semantic Inference for Semi-Supervised Semantic Segmentation
HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
Hierarchical Collaboration for Referring Image Segmentation
InterTeach: A Novel Approach for Semi-Supervised Medical Image Segmentation Using Cooperative Teacher-Student Networks
An Organ-aware Diagnosis Framework for Radiology Report Generation
Adaptive Fuzzy Positive Learning for Annotation-Scarce Semantic Segmentation
Textual Grounding for Open-vocabulary Visual Information Extraction in Layout-Diversified Documents
ParCo: Part-Coordinating Text-to-Motion Synthesis
Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion
Parallel Vertex Diffusion for Unified Visual Grounding
Protein-Ligand Interaction Prior For Binding aware 3D Molecule Diffusion Models
Fine-grained Simulation and Adaptation for Granularity-aware Interactive Segmentation
Model Subject-Driven Generation as Building a Derived Class
Training-Free Transformer Architecture Search With Zero-Cost Proxy Guided Evolution
HARIS: Human-Like Attention for Reference Image Segmentation
2023
23 outputsFuzzy Positive Learning for Semi-supervised Semantic Segmentation
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
High-frequency Stereo Matching Network
Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment
TG-VQA: Ternary Game of Video Question Answering
WiCo: Win-win Cooperation of Bottom-up and Top-down Referring Image Segmentation
TopoSeg: Topology-Aware Nuclear Instance Segmentation
LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation
Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
Multiple sequence-alignment-based RNA language model and its application to structural inference
Flexible Alignment Super-Resolution Network for Multi-Contrast Magnetic Resonance Imaging
Weakly-Supervised 3D Spatial Reasoning for Text-based Visual Question Answering
Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild
Recurrent Fine-Grained Self-Attention Network For Video Crowd Counting
Learning Task-Aligned Mask Query For Instance Segmentation
Two-stage Deep Learning Segmentation for Tiny Brain Regions
Object-Aware Transfer-based Black-box Adversarial Attack on Object Detector
2022
14 outputsDifference in Euclidean Norm Can Cause Semantic Divergence in Batch Normalization
Dual Complementary Prototype Learning for Few-Shot Segmentation
Robust and Hierarchical Spatial Relation Analysis for Traffic Forecasting
An Inclusive Task-Aware Framework for Radiology Report Generation
CENet: Consolidation-and-Exploration Network for Continuous Domain Adaptation
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
Locality guidance for improving vision transformers on tiny datasets
Efficient Algorithm and Hardware Architecture for Rate Estimation in Mode Decision of AVS3
Joint learning of object graph and relation graph for visual question answering
Training-free Transformer Architecture Search
Carrying Out CNN Channel Pruning in a White Box
Running ahead of evolution - AI based simulation for predicting future high-risk SARS-CoV-2 variants
AI-based simulation for predicting future high-risk SARS-CoV-2 variants. A joint project shortlisted for the 2022 ACM Gordon Bell Special Prize for HPC-Based COVID-19 Research.
Semi-supervised CT lesion segmentation using uncertainty-based data pairing and SwapMix
2021
12 outputsMemory attention networks for skeleton-based action recognition
Cola: Weakly-supervised temporal action localization with snippet contrastive learning
Discover cross-modality nuances for visible-infrared person re-identification
Annotation-efficient deep learning for automatic medical image segmentation
A hybrid-attention nested UNet for nuclear segmentation in histopathological images
MIGO-NAS: Towards fast and generalizable neural architecture search
Joint segmentation and detection of COVID-19 via a sequential region generation network
Dynamic perception framework for fine-grained recognition
Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
2020
7 outputsSRN: Side-Output Residual Network for Object Reflection Symmetry Detection and Beyond
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
An Automated Method with Feature Pyramid Encoder and Dual-Path Decoder for Nuclei Segmentation
Semi-supervised Natural Face De-occlusion
BCData: A Large-Scale Dataset and Benchmark for Cell Detection and Counting
A dataset and benchmark for detecting and counting positive and negative tumor cells. Images and HDF5 coordinate annotations are divided into training, validation, and test splits.
Dataset structure & loading example
BCData/images/{train,validation,test}/
BCData/annotations/{train,validation,test}/{positive,negative}/import h5py
import numpy as np
gt_path = "BCData/annotations/train/positive/10.h5"
with h5py.File(gt_path, "r") as gt_file:
coordinates = np.asarray(gt_file["coordinates"])2019
6 outputsGuest Editors’ Introduction to the Special Section on Compact and Efficient Feature Representation and Learning in Computer Vision
Deep contour and symmetry scored object proposal
From BoW to CNN: Two decades of texture representation for texture classification
Tumor Tissue Segmentation for Histopathological Images
2011
1 outputs2010
1 outputsOngoing
2 outputs
Pengcheng Shennong
AI-assisted targeted drug design and biomolecular research.
MetaFold
Protein structure prediction research using the Pengcheng Cloudbrain II AI computing cluster.
No research outputs match these filters. Try another title, author or research area.
This archive includes the publications listed on the lab website. For a broader citation record, visit Google Scholar.
Google ScholarPatents & software copyrights · 21
- 高志强，陈杰，乔鹏冲，田永鸿. 一种胸部CT图像病灶分割模型的训练方法及系统[P].申请号202110705914.8，2021年6月24日
- 黄锦发，陈杰，高志强，田永鸿 . 一种基于Transformer的CT报告生成方法[P].申请号202110795676.4，2021年7月14日
- 陈杰、田永鸿、高文、王中岐、王林. 一种基于任务感知的报告自动生成方法及装置[P].申请号202211156398.9，2022年9月22日 初审通过
- 陈杰、田永鸿、高文、王中岐、王林. 利用自然语言模型自动生成结构化报告的方法及相关设备[P].申请号202211078506.5，2022年9月5日 初审通过
- 田永鸿、杨文明、王天誉、陈杰. 一种药物-靶点交互作用预测方法、系统及终端设备[P].申请号202210632799.0，2022年6月7日
- 王珊珊，黄纬键，郑海荣，陈杰，周晖晖，田永鸿. 基于人机交互的模型训练方法、装置、终端及存储介质[P].申请号202211222416.9，2022年10月8日
- 王珊珊、吴若有、黄纬键、陈杰. 一种基于对抗样本的医学图像重建方法及相关装置[P]. 申请号202211425844.1，2022年11月16日
- 陈杰、田永鸿、高文、黄显淞、孔子尚.一种基于多任务学习的图像清洁度评估方法及相关装置[P].申请号202211475103.4，2022年11月23日
- 陈杰、田永鸿、高文、黄显淞、孔子尚.一种基于可学习方向导数的病灶边缘检测方法及相关装置[P].申请号202211475402.8，2022年11月23日
- 陈杰、田永鸿、高文、王中岐、王书博.一种基于区域互补聚合的人群计数方法及相关装置[P].申请号202211384415.4，2022年11月7日
- 高文，陈杰，田永鸿，施振辉、夏源. 基于图路径搜索和语义索引的医疗问答系统[P].申请号202211709241.4，2022年12月29日
- 高文，陈杰，田永鸿，王兆玮.一种基于数据增强的肝脏CT肿瘤分割方法[P].申请号202211623471.9，2022年12月16日
- 陈杰、田永鸿、高文、王中岐、任前. 基于注意力机制的小样本分割方法、装置、终端及介质[P].申请号202211569888.1，2022年12月8日
- 陈杰，田永鸿，高文，黄显淞，黄钟毅.一种基于中心点的细胞核分割方法[P].申请号202211705880.3，2022年12月29日
- 高文，陈杰，田永鸿，徐凡，耿睿哲.一种多尺度空间特征增强方法及装置[P].申请号202211569881.X，2022年12月8日
- 田永鸿，陈杰，高文，徐凡，张弛.一种基于领域对关联的迁移学习方法及装置[P].申请号202211581443.5，2022年12月9日
- 田永鸿，高文，陈杰，徐凡，耿睿哲.一种基于上下文特征融合的细胞核分割方法及相关设备[P].申请号202211580495.0，2022年12月9日
- 田永鸿，陈杰，高文，徐凡，张弛.基于自适应参数隔离的迁移学习方法、装置、终端及介质[P].申请号202211579420.0，2022年12月8日
- 陈杰、田永鸿、高文、黄显淞、徐凡、王中岐. 药物与蛋白质设计服务管理系统（软件著作权）.2022R11L1872673
- 李代禧、陈杰、田永鸿、高文. 基于靶位结构和结合自由能的蛋白药物筛选软件（软件著作权）.2022R11L1988060
- 李代禧、陈杰、田永鸿、高文. 基于Gromacs的分子模拟软件（软件著作权）.2022R11L1995041
Honors & awards
First Prize, National Science and Technology Progress Award.
Zhiwei Nie received a Youth Outstanding Paper Award at the World Artificial Intelligence Conference for “A unified evolution-driven deep learning framework for virus variation driver prediction”.
Zhiwei Nie was named a Qingyuan Scholar by the Chinese Association for Artificial Intelligence.Source
Second Prize in the national final and First Prize in Guangdong, 2024 “Data Elements ×” Competition.Source
“Zu Chongzhi” Annual Major Achievement Award for Frontier Innovation in Artificial Intelligence.Source
Special Prize, Guangdong Science and Technology Progress Award.Source
The joint team involving our group was one of three finalists worldwide for the ACM Gordon Bell Special Prize for HPC-Based COVID-19 Research, and the only finalist team from China.Source
First place on a CAMEO monthly leaderboard for protein structure prediction.Source
Second Prize, National Science and Technology Progress Award: Local Modeling of Visual Patterns and Nonlinear Feature Acquisition — Theory and Methods.
First place in the IAPR ICB 2006 Face Verification Competition, organized by Josef Kittler, University of Surrey, UK.
Second Prize, National Science and Technology Progress Award: Face Recognition — Theory, Technology, Systems and Applications.
First Prize in Face Verification, First China Biometrics Competition (BVC 2004).
Publication announcements & archive
2025
2 papers accepted to AAAI. Congratulations to Zishan Shu and Ruochong Zheng.
1 paper accepted to IEEE TMM. Congratulations to Yuke Li.
2 papers accepted to ICCV. Congratulations to Zesen Cheng and Yian Zhao.
2 papers accepted to CVPR. Congratulations to Yian Zhao and Bin Chen.
1 paper accepted to IJCAI. Congratulations to Zishan Shu.
3 papers accepted to IEEE TPAMI. Congratulations to Bin Chen, Yian Zhao, and Peng Jin.
1 paper accepted to NAACL. Congratulations to Yihan Zhang.
1 paper accepted to Nature Machine Intelligence. Congratulations to Zhiwei Nie.
2024
2 papers accepted to AAAI. Congratulations to Zesen Cheng and Shiyu Li.
1 paper accepted to IEEE TPAMI. Congratulations to Peng Jin and Hao Li.
2 papers accepted to IEEE TMM. Congratulations to Qiankun Ma and Yuke Li.
1 paper accepted to Nature Machine Intelligence. Congratulations to Zhiwei Nie and Xudong Liu.
1 paper accepted to IJCV. Congratulations to Pengchong Qiao.
4 papers accepted to ECCV. Congratulations to Peng Jin, Mengjun Cheng, Qiran Zou, and Kehan Li.
1 paper accepted to IEEE TMI. Congratulations to Shiyu Li.
1 paper selected as a CVPR Highlight. Congratulations to Yian Zhao.
3 papers accepted to CVPR. Congratulations to Pengchong Qiao and Yian Zhao.
1 paper accepted to ICLR. Congratulations to Zhilin Huang.
2023
1 paper accepted to AAAI. Congratulations to Zesen Cheng.
1 paper accepted to Nucleic Acids Research. Congratulations to Yikun Zhang.
1 paper accepted to NeurIPS. Congratulations to Yu Wang.
1 paper accepted to IEEE TMM. Congratulations to Yiming Liu.
5 papers accepted to ICCV. Congratulations to Pengxu Wei, Yujing Sun, Peng Jin, Kehan Li, Hongliang He, Jun Wang, and Runyi Yu.
1 paper recognized among the top 3% of papers at ICASSP. Congratulations to Bin Fu.
1 paper accepted to IEEE TIP. Congratulations to Hao Li.
3 papers accepted to IJCAI. Congratulations to Peng Jin, Hao Li, and Zesen Cheng.
3 papers selected as CVPR Highlights. Congratulations to Peng Jin, Kehan Li, and Haoliang Zhao.
6 papers accepted to CVPR. Congratulations to Pengchong Qiao, Zesen Cheng, Peng Jin, Kehan Li, Yu Wang, and Haoliang Zhao.
2 papers accepted to ICASSP. Congratulations to Jifan Zhang and Bin Fu.
From the archive
Pengcheng Shennong shortlisted for the ACM Gordon Bell Special Prize for HPC-Based COVID-19 Research, the only shortlisted project from a Chinese team. Learn more about Pengcheng Shennong and the ACM Gordon Bell Prize using the links below.