Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
λScale: Enabling Fast Scaling for Serverless Large Language Model InferenceAlibaba · arXiv (Cornell University)Feb 14, 2025Uni-MoE: Scaling Unified Multimodal LLMs With Mixture of ExpertsAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence67 citationsFeb 13, 2025Adaptive Spatiotemporal Graph Transformer Network for Action Quality AssessmentAlibaba · IEEE Transactions on Circuits and Systems for Video Technology27 citationsFeb 13, 2025Diffusion Models for Molecules: A Survey of Methods and TasksAlibaba · arXiv (Cornell University)6 citationsFeb 13, 2025ORIC: Feature Interaction Detection through Online Random Interaction Chains for Click-Through Rate PredictionAlibaba · ACM Transactions on Knowledge Discovery from Data2 citationsFeb 13, 2025KIMAs: A Configurable Knowledge Integrated Multi-Agent SystemAlibaba · arXiv (Cornell University)Feb 13, 2025Memory Offloading for Large Language Model Inference with Latency SLO GuaranteesAlibaba · arXiv (Cornell University)Feb 12, 2025Preview-Based Category Contrastive Learning for Knowledge DistillationAlibaba · IEEE Transactions on Circuits and Systems for Video Technology3 citationsFeb 11, 2025MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE SolversAlibaba · arXiv (Cornell University)Feb 11, 2025Automatic Database Configuration Debugging using Retrieval-Augmented Language ModelsAlibaba · Proceedings of the ACM on Management of Data12 citationsFeb 10, 2025Knowledge Graph-Guided Retrieval Augmented GenerationAlibaba · arXiv (Cornell University)4 citationsFeb 8, 2025Mint: Cost-Efficient Tracing with All Requests Collection via Commonality and Variability AnalysisAlibaba · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)7 citationsFeb 6, 2025Concerto: Automatic Communication Optimization and Scheduling for Large-Scale Deep LearningAlibaba · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)6 citationsFeb 6, 2025QExplorer: Large Language Model Based Query Extraction for Toxic Content ExplorationAlibaba · arXiv (Cornell University)Feb 6, 2025Multi-Label Test-Time Adaptation with Bound Entropy MinimizationAlibaba · arXiv (Cornell University)Feb 6, 2025Flips: A Flexible Partitioning Strategy Near Memory Processing Architecture for Recommendation SystemAlibaba · IEEE Transactions on Parallel and Distributed SystemsFeb 6, 2025Large Language Model as Universal Retriever in Industrial-Scale Recommender SystemAlibaba · arXiv (Cornell University)Feb 5, 2025Understanding Operational CDN Live Streaming: A Measurement Study on Performance, Costs, and EnhancementsAlibaba · IEEE Transactions on Circuits and Systems for Video Technology4 citationsFeb 4, 2025STAIR: Improving Safety Alignment with Introspective ReasoningAlibaba · arXiv (Cornell University)1 citationFeb 4, 2025KG-prompt: Interpretable knowledge graph prompt for pre-trained language modelsAlibaba · Knowledge-Based Systems9 citationsFeb 1, 2025Maximum Inner Product is Query-Scaled Nearest NeighborAlibaba · Proceedings of the VLDB Endowment3 citationsFeb 1, 2025Agamotto: Scheduling of Deadline-Oriented Incremental Query Execution under Uncertain Resource PriceAlibaba · Proceedings of the VLDB EndowmentFeb 1, 2025MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior ModelingAlibaba · arXiv (Cornell University)Feb 1, 2025TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-OnAlibaba · International Journal of Computer Vision9 citationsJan 31, 2025Dual discriminator GANs with multi-focus label matching for image-aware layout generationAlibaba · Displays5 citationsJan 31, 2025