Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
FastTTS: Accelerating Test-Time Scaling for Edge LLM ReasoningMicrosoft · arXiv (Cornell University)2 citationsAug 29, 2025$Δ$-Motif: Parallel Subgraph Isomorphism via Tabular Operations for Scalable Layout SelectionNVIDIA · arXiv (Cornell University)2 citationsAug 29, 2025WoundcareVQA: A multilingual visual question answering benchmark dataset for wound careMicrosoft · Journal of Biomedical Informatics2 citationsAug 29, 2025AI-Augmented Agile Project Management: A Framework for Smart Decision Making and Risk MitigationMicrosoft · Global Conference on Information Technology and Communication Networks (GITCON)Aug 29, 2025Secure Data Transmission in IoT-Cloud Systems: A Lightweight Encryption ApproachMicrosoft · Global Conference on Information Technology and Communication Networks (GITCON)Aug 29, 2025Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM InferenceMicrosoft · arXiv (Cornell University)Aug 29, 2025CryptographyMicrosoft · Oberwolfach ReportsAug 29, 2025Diffusion Models for Image Restoration and Enhancement: A Comprehensive SurveyMicrosoft · International Journal of Computer Vision219 citationsAug 28, 2025Echoes in AI: Quantifying lack of plot diversity in LLM outputsMicrosoft · Proceedings of the National Academy of Sciences46 citationsAug 28, 2025Understanding, Protecting, and Augmenting Human Cognition with Generative AI: A Synthesis of the CHI 2025 Tools for Thought WorkshopMicrosoft · arXiv (Cornell University)20 citationsAug 28, 2025MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMsAlibaba · arXiv (Cornell University)14 citationsAug 28, 2025Learning to Generate Unit Test via Adversarial Reinforcement LearningMicrosoft · arXiv (Cornell University)11 citationsAug 28, 2025OLMoASR: Open Models and Data for Training Robust Speech Recognition ModelsAllen Institute for AI · arXiv (Cornell University)5 citationsAug 28, 2025AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model ServingMicrosoft · arXiv (Cornell University)3 citationsAug 28, 2025Compressing Vision Transformer from the View of Model Property in Frequency DomainAlibaba · International Journal of Computer Vision3 citationsAug 28, 2025Unveiling Logic Bugs in SPJG Query Optimizations within DBMSAlibaba · ACM Transactions on Database Systems1 citationAug 28, 2025SEAL: Structure and Element Aware Learning to Improve Long Structured Document RetrievalAlibaba · arXiv (Cornell University)Aug 28, 2025ActLoc: Learning to Localize on the Move via Active Viewpoint SelectionMicrosoft · arXiv (Cornell University)Aug 28, 2025Intent-Driven Network Management with Multi-Agent LLMs: The Confucius FrameworkMeta · ACM SIGCOMM Conference (SIGCOMM)40 citationsAug 27, 2025MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts TrainingMeta · ACM SIGCOMM Conference (SIGCOMM)29 citationsAug 27, 2025Towards LLM-Based Failure Localization in Production-Scale NetworksAlibaba · ACM SIGCOMM Conference (SIGCOMM)25 citationsAug 27, 2025New frontiers in artificial intelligence for biodiversity research and conservation with multimodal language modelsMicrosoft · Methods in Ecology and Evolution21 citationsAug 27, 2025Falcon: A Reliable, Low Latency Hardware TransportAlphabet, Meta, Microsoft, NVIDIA · ACM SIGCOMM Conference (SIGCOMM)20 citationsAug 27, 2025SyCCL: Exploiting Symmetry for Efficient Collective Communication SchedulingAlibaba · ACM SIGCOMM Conference (SIGCOMM)19 citationsAug 27, 2025Alibaba Stellar: A New Generation RDMA Network for Cloud AIAlibaba · ACM SIGCOMM Conference (SIGCOMM)19 citationsAug 27, 2025