Publications
Equal contribution
Corresponding author
Project Leader
ALL (151 papers)
【BEAKER】An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories.
Advances in Neural Information Processing Systems,
Sydney & Atlanta & Paris,
2026.
【PhotoFlow】Agentic 3D Virtual Photography Missions.
Advances in Neural Information Processing Systems,
Sydney & Atlanta & Paris,
2026.
【ProCLIP】Progressive Vision-Language Alignment via LLM-based Embedder.
Advances in Neural Information Processing Systems,
Sydney & Atlanta & Paris,
2026.
【RISE-Video】Can Video Generators Decode Implicit World Rules.
Advances in Neural Information Processing Systems, ED Track,
Sydney & Atlanta & Paris,
2026.
【SkillLens】From Raw Experience to Skill Consumption A Systematic Study of Model-Generated Agent Skills.
Advances in Neural Information Processing Systems,
Sydney & Atlanta & Paris,
2026.
【SkillOpt】Executive Strategy for Self-Evolving Agent Skills.
Advances in Neural Information Processing Systems,
Sydney & Atlanta & Paris,
2026.
【WorldForge】Forging Unified World Modeling into Video Generation.
Advances in Neural Information Processing Systems,
Sydney & Atlanta & Paris,
2026.
【RSTalker】Beyond Text Bridging Speech and Satellite Imagery for Efficient Visual Grounding.
IEEE Transactions on Geoscience and Remote Sensing,
2024.
【Bench2Dex】Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands.
arXiv,
2609.15726,
2026.
【V-ICAL Bench】Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments.
arXiv,
2609.15683,
2026.
Towards Vision-Language Geo-Foundation Model A Survey.
The Photogrammetric Record,
2026.
【DMRL】Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation.
arXiv,
2609.0217,
2026.
【FIRM-Video】Check Before You Score for Reliable Text-to-Video Reward Modeling.
arXiv,
2608.21839,
2026.
【OmniInteract】Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants.
Empirical Methods in Natural Language Processing,
Budapest, Hungary,
2026.
【T-STAR】A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video.
arXiv,
2607.21228,
2026.
Context-Aware Aerial Object Detection Leveraging Inter-Object and Background Relationships.
The 9th Chinese Conference on Pattern Recognition and Computer Vision,
Harbin Asian Winter Games Hall,
2026.
【IG-Bench】Ideas Have Genomes Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation.
arXiv,
2607.08758,
2026.
【ACE-Brain-0.5】A Unified Embodied Foundational Model for Physical Agentic AI.
arXiv,
2607.04426,
2026.
【Beyond Vision】How Language affects Visual Grounding in UAV Imagery.
The International Archives of the Photogrammetry,
49, 651-656,
2026.
【DisciplineGen-1M】A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing.
arXiv,
2607.0229,
2026.
【EvoTok】A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation.
European Conference on Computer Vision,
Malmö, Sweden,
2026.
【GRADE】Benchmarking Discipline-Informed Reasoning in Image Editing.
European Conference on Computer Vision,
Malmö, Sweden,
2026.
【RGBT-Ground】Visual Grounding Beyond RGB in Complex Real-World Scenarios.
European Conference on Computer Vision,
Malmö, Sweden,
2026.
【SCL-MGSM】Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection.
European Conference on Computer Vision,
Malmö, Sweden,
2026.
Data-Driven Vision-Language Models for Remote Sensing A survey.
IEEE Geoscience and Remote Sensing Magazine,
2026.
【Moment-Video】Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events.
arXiv,
2606.02522,
2026.
【ResearchClawBench】A benchmark for end-to-end autonomous scientific research.
arXiv,
2606.07591,
2026.
【SpaceDG】Benchmarking Spatial Intelligence under Visual Degradation.
arXiv,
2605.22536,
2026.
【ToxiMol】Breaking Bad Molecules Are MLLMs Ready for Structure-Level Molecular Detoxification?.
32nd SIGKDD Conference on Knowledge Discovery and Data Mining - AI for Sciences Track,
Jeju, Korea,
2026.
【SafeSteer】A Decoding-level Defense Mechanism for Multimodal Large Language Models.
Association for Computational Linguistics,
San Diego, California,
2026.
【CTAOD-RS】Continual Test-Time Adaptive Object Detection in Remote Sensing Images via Spectral Routing and Historical Reconstruction.
IEEE Transactions on Circuits and Systems for Video Technology,
2026.
【Holi-Spatial】Evolving Video Streams into Holistic 3D Spatial Intelligence.
International Conference on Machine Learning,
Seoul, South Korea,
2026.
【PhoStream】Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios.
International Conference on Machine Learning,
Seoul, South Korea,
2026.
【DPN-LE】Dual Personality Neuron Localization and Editing for Large Language Models.
Association for Computational Linguistics,
San Diego, California,
2026.
【MM-WebAgent】A Hierarchical Multimodal Web Agent for Webpage Generation.
arXiv,
2604.15309,
2026.
【HiProto】Hierarchical Prototype Learning for Interpretable Object Detection Under Low-quality Conditions.
arXiv,
2604.13981,
2026.
【Video-MME-v2】Towards the Next Stage in Benchmarks for Comprehensive Video Understanding.
arXiv,
2604.05015,
2026.
【Rt-LRM】Red Teaming Large Reasoning Models.
Association for Computational Linguistics,
San Diego, California,
2026.
【Safe-FedLLM】Delving into the Safety of Federated Large Language Models.
Association for Computational Linguistics,
San Diego, California,
2026.
【DiffER】Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models.
Association for Computational Linguistics,
San Diego, California,
2026.
【BizGenEval】A Systematic Benchmark for Commercial Visual Content Generation.
arXiv,
2603.25732,
2026.
【CrossEarth-SAR】A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation.
arXiv,
2603.12008,
2026.
【FIRM】Trust Your Critic Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation.
arXiv,
2603.12247,
2026.
【CourtSI】Stepping VLMs onto the Court Benchmarking Spatial Intelligence in Sports.
arXiv,
2603.09896,
2026.
【InternVL-U】Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing.
arXiv,
2603.09877,
2026.
【ACE-Brain-0】Spatial Intelligence as a Shared Scaffold for Universal Embodiments.
arXiv,
2603.03198,
2026.
【AdapTok】Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space.
Computer Vision and Pattern Recognition,
Denver Colorado,
2026.
【CrossEarth-Gate】Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation.
Computer Vision and Pattern Recognition,
Denver Colorado,
2026.
【GeoViS】Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding.
Computer Vision and Pattern Recognition,
Denver Colorado,
2026.
【PWOOD】Partial Weakly-Supervised Oriented Object Detection.
Computer Vision and Pattern Recognition,
Denver Colorado,
2026.
【SpatialRetrievalAD】Spatial Retrieval Augmented Autonomous Driving.
Computer Vision and Pattern Recognition,
Denver Colorado,
2026.
【CrossWeaver】Towards Efficient Cross-Modal Interweaving and Decoupling for Weakly-Aligned Multispectral Object Detection.
Computer Vision and Pattern Recognition,
Denver Colorado,
2026.
【GeoEyes】On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery.
arXiv,
2602.14201,
2026.
【SAPNet++】Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
2026.
【CoLin】1%>100% High-Efficiency Visual Adapter with Complex Linear Projection Optimization.
arXiv,
2602.10513,
2026.
【Interleave-VLA】Enhancing Robot Manipulation with Interleaved Image-Text Instructions.
International Conference on Learning Representations,
Rio de Janeiro, Brazil,
2026.
【OF-Diff】Object Fidelity Diffusion for Remote Sensing Image Generation.
International Conference on Learning Representations,
Rio de Janeiro, Brazil,
2026.
【Point2RBox-v3】Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization.
International Conference on Learning Representations,
Rio de Janeiro, Brazil,
2026.
【SpaCE-10】A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence.
International Conference on Learning Representations,
Rio de Janeiro, Brazil,
2026.
【SPWOOD】Sparse Partial Weakly-Supervised Oriented Object Detection.
International Conference on Learning Representations,
Rio de Janeiro, Brazil,
2026.
【RSCoVLM】Co-Training Vision Language Models for Remote Sensing Multi-task Learning.
Remote Sensing,
2026.
【CastDet】Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation.
International Journal of Computer Vision,
2026.
【CrossEarth】Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
2025.
【SGI-Bench】Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows.
arXiv,
2512.16969,
2025.
【Visionary】The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform.
arXiv,
2512.08478,
2025.
Large Multimodal Models Evaluation A Survey.
SCIENCE CHINA Information Sciences,
2025.
【Earth-Adapter】Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation.
Fortieth AAAI Conference on Artificial Intelligence,
Singapore,
2025.
【LWGANet】A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks.
Fortieth AAAI Conference on Artificial Intelligence,
Singapore,
2025.
【InstructSAM】A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition.
Advances in Neural Information Processing Systems,
San Diego & Mexico City,
2025.
【OPMapper】nhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information.
Advances in Neural Information Processing Systems,
San Diego & Mexico City,
2025.
【GeneMAN】Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data.
Advances in Neural Information Processing Systems,
San Diego & Mexico City,
2025.
【Raw2Drive】Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2).
Advances in Neural Information Processing Systems,
San Diego & Mexico City,
2025.
【RISEBench】Envisioning Beyond the Pixels Benchmarking Reasoning-Informed Visual Editing.
Advances in Neural Information Processing Systems, DB Track,
San Diego & Mexico City,
2025.
【GLEAM】Learning to Match and Explain in Cross-View Geo-Localization.
arXiv,
2509.0745,
2025.
【AVI-Math】Multimodal mathematical reasoning embedded in aerial vehicle imagery:Benchmarking, analysis, and exploration.
ISPRS Journal of Photogrammetry and Remote Sensing,
230, 289-303,
2025.
【PIIP】Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
47(11), 10142-10159,
2025.
【Mono-InternVL-1.5】Towards Cheaper and Faster Monolithic Multimodal Large Language Models.
arXiv,
2507.12566,
2025.
【UniRGB-IR】A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning.
33rd ACM International Conference on Multimedia,
Dublin, Ireland,
2025.
【R3DetGauss】Parameter-efficient fine-tuning for remote sensing image interpretation a survey.
Journal of Image and Graphics,
31(1), 0212-0242,
2023.
【Flexi-FSCIL】Adaptive Knowledge Retention for Breaking the Stability-Plasticity Dilemma in Few-Shot Class-Incremental Learning.
International Conference on Computer Vision,
Honolulu, Hawai'i,
2025.
【GenieBlue】Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices.
International Conference on Computer Vision,
Honolulu, Hawai'i,
2025.
【LRS-VQA】When Large Vision-Language Model Meets Large Remote Sensing Imagery Coarse-to-Fine Text-Guided Token Pruning.
International Conference on Computer Vision,
Honolulu, Hawai'i,
2025.
【SA-Occ】Satellite-Assisted 3D Occupancy Prediction in Real World.
International Conference on Computer Vision,
Honolulu, Hawai'i,
2025.
【SatDiFuser】Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?.
International Conference on Computer Vision,
Honolulu, Hawai'i,
2025.
【AirSpatialBot】A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval.
IEEE Transactions on Geoscience and Remote Sensing,
2025.
【PointOBB-v3】Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection.
International Journal of Computer Vision,
133, 6108–6128,
2025.
【LMMRotate】A Simple Aerial Detection Baseline of Multimodal Language Models.
International Geoscience and Remote Sensing Symposium,
Brisbane, Australia,
2025.
【Mona】5%>100% Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks.
Computer Vision and Pattern Recognition,
Music City Center, Nashville TN,
2025.
【Mono-InternVL】Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training.
Computer Vision and Pattern Recognition,
Music City Center, Nashville TN,
2025.
【Point2RBox-v2】Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances.
Computer Vision and Pattern Recognition,
Music City Center, Nashville TN,
2025.
【RSAR】Restricted State Angle Resolver and Rotated SAR Benchmark.
Computer Vision and Pattern Recognition,
Music City Center, Nashville TN,
2025.
【Wholly-WOOD】Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
47(6), 4438-4454,
2025.
【FLoRA】Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning.
International Conference on Learning Representations,
Singapore,
2025.
【PointOBB-v2】Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection.
International Conference on Learning Representations,
Singapore,
2025.
【UCDNet】Multi-UAV Collaborative 3D Object Detection Network by Reliable Feature Mapping.
IEEE Transactions on Geoscience and Remote Sensing,
63,
2024.
【DiffCLIP】Few-shot Language-driven Multimodal Classifier.
Thirty-Ninth AAAI Conference on Artificial Intelligence,
Philadelphia, Pennsylvania, USA,
2025.
【STAR】A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
47(3), 1832-1849,
2024.
【GeoGround】A Unified Large Vision-Language Model for Remote Sensing Visual Grounding.
arXiv,
2411.11904,
2024.
【Drones Help Drones】A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond.
Advances in Neural Information Processing Systems,
Vancouver, Canada,
2024.
【E2E-MFD】Towards End-to-End Synchronous Multimodal Fusion Detection.
Advances in Neural Information Processing Systems,
Vancouver, Canada,
2024.
【PIIP】Parameter-Inverted Image Pyramid Networks.
Advances in Neural Information Processing Systems,
Vancouver, Canada,
2024.
【CastDet】Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning.
European Conference on Computer Vision,
MiCo Milano, Italy,
2024.
【FreeReal】Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors.
European Conference on Computer Vision,
MiCo Milano, Italy,
2024.
【Auto MC-Reward】Automated Dense Reward Design with Large Language Models for Minecraft.
Computer Vision and Pattern Recognition,
Seattle WA, USA,
2024.
【COBB】Theoretically Achieving Continuous Representation of Oriented Bounding Boxes.
Computer Vision and Pattern Recognition,
Seattle WA, USA,
2024.
【Point2RBox】Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision.
Computer Vision and Pattern Recognition,
Seattle WA, USA,
2024.
【PointOBB】Learning Oriented Object Detection via Single Point Supervision.
Computer Vision and Pattern Recognition,
Seattle WA, USA,
2024.
【ARS-DETR】Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection.
IEEE Transactions on Geoscience and Remote Sensing,
62, 1-15,
2024.
【AlphaRotate】A Rotation Detection Benchmark using TensorFlow.
International Conference on Acoustics, Speech and Signal Processing,
Seoul, Korea,
2024.
【R3DetGauss】Visual Oriented Object Detection via Feature Alignment and Gaussian Parameterization.
SCIENCE CHINA Information Sciences,
53(11), 2250-2265,
2023.
【H2RBox-v2】Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection.
Advances in Neural Information Processing Systems,
New Orleans, Louisiana, USA,
2023.
【CCD】Self-supervised Character-to-Character Distillation for Text Recognition.
International Conference on Computer Vision,
Paris, France,
2023.
【InternGPT】Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language.
arXiv,
2305.05662,
2023.
【SIGA】Self-supervised Implicit Glyph Attention for Text Recognition.
Computer Vision and Pattern Recognition,
Vancouver, Canada,
2023.
【G-Rep】Gaussian Representation for Arbitrary-Oriented Object Detection.
Remote Sensing (2023 Best Paper Awards),
15(3), 757,
2023.
【H2RBox】Horizontal Box Annotation is All You Need for Oriented Object Detection.
International Conference on Learning Representations,
Kigali, Rwanda,
2023.
【KFIoU】The KFIoU Loss for Rotated Object Detection.
International Conference on Learning Representations,
Kigali, Rwanda,
2023.
【PatchDCT】Patch Refinement for High Quality Instance Segmentation.
International Conference on Learning Representations,
Kigali, Rwanda,
2023.
【TIOE】Task Interleaving and Orientation Estimation for High-Precision Oriented Object Detection in Aerial Images.
ISPRS Journal of Photogrammetry and Remote Sensing,
196, 241-255,
2023.
【PVT-SAR】An Arbitrarily Oriented SAR Ship Detector with Pyramid Vision Transformer.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,
16, 291-305,
2022.
【MMRotate】A Rotated Object Detection Benchmark using PyTorch.
30th ACM International Conference on Multimedia, OS Track,
Lisboa, Portugal,
2022.
Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
45(4), 4335-4354,
2022.
【RSDet++】Point-based Modulated Loss for More Accurate Rotated Object Detection.
IEEE Transactions on Circuits and Systems for Video Technology,
32(11), 7869-7879,
2022.
【SCRDet++】Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
45(2), 2384-2399,
2022.
Dual-path Image Inpainting with Auxiliary GAN Inversion.
Computer Vision and Pattern Recognition,
New Orleans, Louisiana,
2022.
On the Arbitrary-Oriented Object Detection Classification based Approaches Revisited.
International Journal of Computer Vision,
130, 1340-1365,
2022.
【KLD】Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence.
Advances in Neural Information Processing Systems,
Virtual,
2021.
【RIDet】Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss.
IEEE Geoscience and Remote Sensing Letters,
19, 1-5,
2021.
Parallel Multi-Resolution Fusion Network for Image Inpainting.
International Conference on Computer Vision,
Virtual,
2021.
【SLA】Sparse Label Assignment for Oriented Object Detection in Aerial Images.
Remote Sensing,
13(14), 2664,
2021.
【GWD】Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss.
International Conference on Machine Learning,
Virtual,
2021.
【DCL】Dense Label Encoding for Boundary Discontinuity Free Rotation Detection.
Computer Vision and Pattern Recognition,
Virtual,
2021.
【R3Det】Refined Single-Stage Detector with Feature Refinement for Rotating Object.
Thirty-Fifth AAAI Conference on Artificial Intelligence,
Vancouver, Canada,
2021.
【RSDet】Learning Modulated Loss for Rotated Object Detection.
Thirty-Fifth AAAI Conference on Artificial Intelligence,
Vancouver, Canada,
2021.
Texture Synthesis Based Thyroid Nodule Detection from Medical Ultrasound Images Interpreting and Suppressing the Adversarial Effect of In-place Manual Annotation.
Frontiers in Bioengineering and Biotechnology,
8, 599,
2019.
【CSL】Arbitrary-Oriented Object Detection with Circular Smooth Label.
European Conference on Computer Vision,
Glasgow, Scotland, UK,
2020.
【FSCascade】Rethinking Classification and Localization for Cascade R-CNN.
30th British Machine Vision Conference,
Cardiff, Wales, UK,
2019.
【SCRDet】Towards More Robust Detection for Small, Cluttered and Rotated Objects.
International Conference on Computer Vision,
Seoul, Korea,
2019.
【FFPN-RL】A Ship Rotation Detection Model in Remote Sensing Images Based on Feature Fusion Pyramid Network and Deep Reinforcement Learning.
Remote Sensing,
10(12), 1922,
2018.
【RFast-RCNN】Building Detection in High Spatial Resolution Remote Sensing Imagery with the U-Rotation Detection Network.
International Journal of Remote Sensing,
40(15), 6036-6058,
2018.
Position Detection and Direction Prediction for Arbitrary-oriented Ships via Multitask Rotation Region Convolutional Neural Network.
IEEE Access,
6, 50839-50849,
2018.
【DCMSNN】A Densely Connected End-to-End Neural Network for Multiscale and Multiscene SAR Ship Detection.
IEEE Access,
6, 20881-20892,
2018.
Object Detection With Head Direction in Remote Sensing Images Based on Rotational Region CNN.
International Geoscience and Remote Sensing Symposium,
Valencia,
2018.
【R-DFPN】Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks.
Remote Sensing,
10(1), 132,
2018.