Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Overcoming Joint Intractability with Lossless Hierarchical Speculative DecodingAlibaba · arXiv (Cornell University)Jan 9LEAPS: An LLM-Empowered Adaptive Plugin in Taobao AI SearchAlibaba · arXiv (Cornell University)Jan 9An interpretable model based on concept and argumentation for tabular dataAlibaba · Scientific Reports3 citationsJan 8Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI RecommendationAlibaba · arXiv (Cornell University)1 citationJan 8Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI RecommendationAlibaba · arXiv (Cornell University)Jan 8Enhancing Multimodal Retrieval via Complementary Information Extraction and AlignmentAlibaba · arXiv (Cornell University)Jan 8AgentOCR: Reimagining Agent History via Optical Self-CompressionAlibaba · arXiv (Cornell University)Jan 8Enhancing Multimodal Retrieval via Complementary Information Extraction and AlignmentAlibaba · arXiv (Cornell University)Jan 8AgentOCR: Reimagining Agent History via Optical Self-CompressionAlibaba · arXiv (Cornell University)Jan 8Retrieval Heads are DynamicAlibaba · arXiv (Cornell University)Jan 7Retrieval Heads are DynamicAlibaba · arXiv (Cornell University)Jan 7Controllable LLM Reasoning via Sparse Autoencoder-Based SteeringAlibaba · arXiv (Cornell University)Jan 7Controllable LLM Reasoning via Sparse Autoencoder-Based SteeringAlibaba · arXiv (Cornell University)Jan 7VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action ModelsAlibaba · arXiv (Cornell University)Jan 6Parallel Latent Reasoning for Sequential RecommendationAlibaba · arXiv (Cornell University)Jan 6Orchestrating optimization passes of machine learning compiler for reducing memory footprints of computation graphsAlibaba · Journal of Systems ArchitectureJan 6Unified Thinker: A General Reasoning Modular Core for Image GenerationAlibaba · arXiv (Cornell University)Jan 6SafeLoad: Efficient Admission Control Framework for Identifying Memory-Overloading Queries in Cloud Data WarehousesAlibaba · arXiv (Cornell University)Jan 5Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length RegulationAlibaba · arXiv (Cornell University)Jan 5SafeLoad: Efficient Admission Control Framework for Identifying Memory-Overloading Queries in Cloud Data WarehousesAlibaba · arXiv (Cornell University)Jan 5Lingshu: Generalist Foundation Model for Unified Multimodal Medical Understanding and ReasoningAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence19 citationsJan 1View-Centric Multiobject Tracking With Homographic Matching in Moving UAVAlibaba · IEEE Transactions on Geoscience and Remote Sensing13 citationsJan 1Multi-Granularity Prediction with Learnable Fusion for Scene Text RecognitionAlibaba · International Journal of Computer Vision5 citationsJan 1Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model AgentsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting4 citationsJan 1SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music ProcessingAlibaba · IEEE Journal of Selected Topics in Signal Processing4 citationsJan 1