Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Widening the bottleneck of lexical choice for non-autoregressive translationAlibaba · Computer Speech & Language1 citationJan 31, 2025Structural and Statistical Texture Knowledge Distillation and Learning for SegmentationAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence9 citationsJan 30, 2025Curricular Subgoals for Inverse Reinforcement LearningAlibaba · IEEE Transactions on Intelligent Transportation Systems2 citationsJan 30, 2025Preserving high-order ego-centric topological patterns in node representation in heterogeneous graphAlibaba · Knowledge-Based SystemsJan 29, 2025Unraveling the anchoring effect of seller’s show on buyer’s show to enhance review helpfulness prediction: A multi-granularity attention network model with multimodal informationAlibaba · Electronic Commerce Research and Applications4 citationsJan 28, 2025Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identificationAlibaba · arXiv (Cornell University)Jan 28, 2025Static Batching of Irregular Workloads on GPUs: Framework and Application to Efficient MoE Model InferenceAlibaba · arXiv (Cornell University)Jan 27, 2025Qwen2.5-1M Technical ReportAlibaba · arXiv (Cornell University)12 citationsJan 26, 2025HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video UnderstandingAlibaba · arXiv (Cornell University)1 citationJan 25, 2025Speech Translation Refinement using Large Language ModelsAlibaba · arXiv (Cornell University)Jan 25, 2025RealCritic: Towards Effectiveness-Driven Evaluation of Language Model CritiquesAlibaba · arXiv (Cornell University)Jan 24, 2025TranSeis: A high precision multitask seismic waveform detectorAlibaba · Computers & Geosciences6 citationsJan 22, 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video UnderstandingAlibaba · arXiv (Cornell University)5 citationsJan 22, 2025Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert ModelsAlibaba · arXiv (Cornell University)Jan 21, 2025Topology-joint Curvilinear Segmentation Network using Confidence-based Bezier Topological RepresentationAlibaba · Engineering Applications of Artificial Intelligence5 citationsJan 18, 2025Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!Alibaba · arXiv (Cornell University)1 citationJan 18, 2025Privacy-preserving coordinated operation of cross-enterprise data centersAlibaba · Applied Energy15 citationsJan 17, 2025MFCQA: Multi-Range Feature Cross-Attention Mechanism for no-reference image quality assessmentAlibaba · Knowledge-Based Systems5 citationsJan 17, 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through ThinkingAlibaba · arXiv (Cornell University)Jan 16, 2025A comprehensive review of network pruning based on pruning granularity and pruning time perspectivesAlibaba · Neurocomputing24 citationsJan 14, 2025Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question AnsweringAlibaba · arXiv (Cornell University)1 citationJan 14, 2025Active Sampling for Node Attribute Completion on GraphsAlibaba · arXiv (Cornell University)Jan 14, 2025Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual AwarenessAlibaba · arXiv (Cornell University)Jan 14, 2025Unsupervised Query Routing for Retrieval Augmented GenerationAlibaba · arXiv (Cornell University)Jan 14, 2025Adaptive Capacity Provisioning for Carbon-Aware Data Centers: A Digital Twin-Based ApproachAlibaba · IEEE Transactions on Sustainable Computing16 citationsJan 13, 2025