Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Memorization Dynamics in Knowledge Distillation for Language ModelsMeta · arXiv (Cornell University)Jan 21LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space IntegrationMicrosoft · arXiv (Cornell University)Jan 21Learning from Synthetic Data: Limitations of ERMAlphabet · arXiv (Cornell University)Jan 21Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning PerspectiveiFlytek · arXiv (Cornell University)Jan 21Unified Event-Sourced CQRS Architecture for Continuous Compliance Monitoring and Automated Regulatory ReportingMicrosoft · International Journal on Science and TechnologyJan 21Performance and robustness of signal-dependent vs. signal-independent binaural signal matching with wearable microphone arraysMeta · EURASIP Journal on Audio Speech and Music ProcessingJan 21Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic SearchMicrosoft · arXiv (Cornell University)2 citationsJan 20Future of quantum computingAlphabet · Quantum Machine Intelligence2 citationsJan 20Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular ObservationsMicrosoft · arXiv (Cornell University)1 citationJan 20OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language ModelsUpstage · arXiv (Cornell University)1 citationJan 20SceneVTG++: Controllable Multilingual Visual Text Generation in the WildAlibaba · IEEE Transactions on Circuits and Systems for Video Technology1 citationJan 20Collaborative Prediction of Cloud DRAM Failures With Rules and Machine LearningAlibaba · IEEE Transactions on Computers1 citationJan 20VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool IntegrationMicrosoft · arXiv (Cornell University)Jan 20ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction EvolutionMicrosoft · arXiv (Cornell University)Jan 20AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple AgentMicrosoft · arXiv (Cornell University)Jan 20"Range as a Key" is the Key! Fast and Compact Cloud Block Store Index with RASKAlibaba · arXiv (Cornell University)Jan 20GETL: An Extract-Transform-Load Framework Across Graph Models in Graph WarehouseAlibaba · IEEE Transactions on Knowledge and Data EngineeringJan 20Toward Robust Low-Latency Live Streaming: Measurement, Prediction, and Rate Adaptation Under UncertaintyAlibaba · IEEE Transactions on Mobile ComputingJan 20Self-Reflective Memory Consolidation in Agentic ArchitecturesMeta · International Journal of Computer ApplicationsJan 20ThinkFL: Self-Refining Failure Localization for Microservice Systems via Reinforcement Fine-TuningAlibaba · ACM Transactions on Software Engineering and Methodology11 citationsJan 19Conditional Modeling-Based Automatic Video SummarizationNVIDIA · ACM Transactions on Multimedia Computing Communications and Applications5 citationsJan 19On the Use of LLMs for Relevance LabellingMicrosoft · ACM Transactions on Information Systems4 citationsJan 19Charting Uncertain Waters: A Socio-Technical Roadmap for Sustaining Open Source Communities in the Age of GenAIMicrosoft · ACM Transactions on Software Engineering and Methodology3 citationsJan 19The Case for Cardinality Lower BoundsMicrosoft · arXiv (Cornell University)1 citationJan 19ROMA: A Read-Only-Memory-based Accelerator for QLoRA-based On-Device LLMMicrosoft · Asia and South Pacific Design Automation Conference (ASP-DAC)Jan 19