Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
RSGPT: A remote sensing vision language model and benchmarkAlibaba · ISPRS Journal of Photogrammetry and Remote Sensing220 citationsApr 12, 2025Unlocking the Power of LSTM for Long Term Time Series ForecastingAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence86 citationsApr 11, 2025Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient InferenceAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence54 citationsApr 11, 2025SWIFT: A Scalable Lightweight Infrastructure for Fine-TuningAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence46 citationsApr 11, 2025CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based VerificationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence25 citationsApr 11, 2025Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI FeedbackAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence24 citationsApr 11, 2025Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image GenerationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence15 citationsApr 11, 2025Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection GuidanceAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence14 citationsApr 11, 2025Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech DeepfakesAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence13 citationsApr 11, 2025One Node One Model: Featuring the Missing-Half for Graph ClusteringAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence10 citationsApr 11, 2025MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image SynthesisAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence9 citationsApr 11, 2025MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors RoutingAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence9 citationsApr 11, 2025Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model Using 3D Whole-Body CT ScansAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence8 citationsApr 11, 2025Speech Recognition Meets Large Language Model: Benchmarking, Models, and ExplorationAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence7 citationsApr 11, 2025Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model OptimizersAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence6 citationsApr 11, 2025HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table UnderstandingAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence6 citationsApr 11, 2025Multi-View Collaborative Learning Network for Speech Deepfake DetectionAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence6 citationsApr 11, 2025ContextHOI: Spatial Context Learning for Human-Object Interaction DetectionAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence5 citationsApr 11, 2025RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style GuidanceAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence5 citationsApr 11, 2025Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented SamplesAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence5 citationsApr 11, 2025ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token TrimmingAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence5 citationsApr 11, 2025HLMEA: Unsupervised Entity Alignment Based on Hybrid Language ModelsAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence5 citationsApr 11, 2025ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction DataAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence4 citationsApr 11, 2025POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position SearchAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence4 citationsApr 11, 2025No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier MethodsAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence4 citationsApr 11, 2025