Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
VC-Tooler: Learning Compositional and Adaptive Visual Tool UseAlibaba · arXiv (Cornell University)Aug 3AdaThinkV: Adaptive Thinking for Token-Efficient Video ReasoningAlibaba · arXiv (Cornell University)Aug 3UEmbed: Unified Sparse and Dense Multimodal EmbeddingsAlibaba · arXiv (Cornell University)Aug 3From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task EvolutionAlibaba · arXiv (Cornell University)Aug 3SPAE: Spectrally Guided Autoencoder for Pretrained Visual LatentsAlibaba · arXiv (Cornell University)Aug 2Credit the Right Box: Marginal Contribution Assignment for Structured Visual PerceptionAlibaba · arXiv (Cornell University)Aug 2Spatio-temporal heterogeneous graph-based modeling and temperature prediction for data center indoor systemAlibaba · Applied EnergyAug 2Semantic Alignment-Driven Time Series Forecasting with Large Language ModelsAlibaba · International Conference on Computer Science and Blockchain (CCSB)Aug 1Narwhal: Breaking the Local Boundary via Disaggregated Memory Scheduling for Alibaba AnalyticDBAlibaba · Proceedings of the VLDB EndowmentAug 1Bridging LLMs and Database Systems: A Deep Dive into Enhanced Relational OperatorsAlibaba · Proceedings of the VLDB EndowmentAug 1Nova: A Multi-Purpose Vector Engine for Low-Latency, Multi-Tenant, and Cross-Table Hybrid RetrievalAlibaba · Proceedings of the VLDB EndowmentAug 1Efficient and Reliable Systems for Building Foundation Models at ScaleAlibaba · Proceedings of the VLDB EndowmentAug 1PolarKV: Tier Locally, Serve Globally-A KV Cache over Cloud Memory and StorageAlibaba · Proceedings of the VLDB EndowmentAug 1SCALAR++: Efficient Controllable Generation via Scale-wise Visual Autoregressive LearningAlibaba · International Journal of Computer VisionAug 1ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba AnalyticDBAlibaba · Proceedings of the VLDB EndowmentAug 1Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving TracesAlibaba · arXiv (Cornell University)Aug 1MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping AgentsAlibaba · arXiv (Cornell University)Jul 31LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language ModelsAlibaba · arXiv (Cornell University)Jul 30Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video UnderstandingAlibaba · arXiv (Cornell University)Jul 30Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning CapabilitiesAlibaba · arXiv (Cornell University)Jul 30SKILL-KD: Contrastive Skill Distillation for LLM AgentsAlibaba · arXiv (Cornell University)Jul 30LoopMemGR: From Behavior Logs to Evolving Memory for Generative RecommendationAlibaba · arXiv (Cornell University)Jul 30BridgeAlign: Bridging Preference Alignment for Humanities and Social SciencesAlibaba · arXiv (Cornell University)Jul 29Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill OverfittingAlibaba · arXiv (Cornell University)Jul 29SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident ResponseAlibaba · arXiv (Cornell University)Jul 29