Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of AdaptivityAlphabet · arXiv (Cornell University)Feb 17A memory fabric for conversational AI agents enabling shared and persistent multiuser memoryMicrosoft · Discover Artificial IntelligenceFeb 17LLM Scalability Risk for Agentic-AI and Model Supply Chain SecurityAlphabet · Journal of Computer Information SystemsFeb 17MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral AdaptationAlibaba · ACM International Conference on Web Search and Data Mining (WSDM)3 citationsFeb 16Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User ModelAlibaba · ACM International Conference on Web Search and Data Mining (WSDM)2 citationsFeb 16Symmetry in language statistics shapes the geometry of model representationsGoogle DeepMind · arXiv (Cornell University)1 citationFeb 16MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product UnderstandingAlibaba · ACM International Conference on Web Search and Data Mining (WSDM)1 citationFeb 16Multi-faceted, multi-scale, and multi-task trend learning for denied check-in prediction on online travel platformsAlibaba · Data Mining and Knowledge Discovery1 citationFeb 16tensorFM: Low-Rank Approximations of Cross-Order Feature InteractionsTechnology Innovation Institute · arXiv (Cornell University)Feb 16Key Considerations for Domain Expert Involvement in LLM Design and Evaluation: An Ethnographic StudyMicrosoft · arXiv (Cornell University)Feb 16SA-SSL-MOS: Self-supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech AssessmentAlphabet · arXiv (Cornell University)Feb 16Qute: Towards Quantum-Native DatabaseMicrosoft · arXiv (Cornell University)Feb 16Cold-Start Personalization via Training-Free Priors from Structured World ModelsAllen Institute for AI · arXiv (Cornell University)Feb 16Learning State-Tracking from Code Using Linear RNNsMicrosoft · arXiv (Cornell University)Feb 16WebWorld: A Large-Scale World Model for Web Agent TrainingAlibaba · arXiv (Cornell University)Feb 16Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent LearningAlibaba · arXiv (Cornell University)Feb 16Explainable Token-level Noise Filtering for LLM Fine-tuning DatasetsAlibaba · arXiv (Cornell University)Feb 16Scaling Beyond Masked Diffusion Language ModelsNVIDIA · arXiv (Cornell University)Feb 16ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation LearningAlibaba · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16MC#: Mixture Compressor for Mixture-of-Experts Large ModelsNVIDIA · IEEE Transactions on Pattern Analysis and Machine IntelligenceFeb 16Sharpness-aware Federated Graph LearningiFlytek · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16Privacy-preserved LLM Cascade via CoT-enhanced Policy LearningAlphabet · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16WSDM CUP 2026: Multilingual RetrievalAllen Institute for AI · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16RankGraph-Context: Empowering Different Industrial Recommendation System StagesMeta · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16RankID: A Unified Semantic ID Learned through Multi-Stage Semantic Alignment of Multimodal FeaturesMeta · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16