Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SmartNS: Enabling Line-rate and Flexible Network Stack with SmartNICAlibaba · European Conference on Computer SystemsApr 24TCO-driven Storage Provisioning for Exascale Data CentersAlphabet, Microsoft · European Conference on Computer SystemsApr 24FlashPS: Efficient Generative Image Editing with Mask-aware Caching and SchedulingAlibaba · European Conference on Computer SystemsApr 24Maya: Optimizing Deep Learning Training Workloads using GPU Runtime EmulationNVIDIA · European Conference on Computer SystemsApr 24Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-DesignMicrosoft · European Conference on Computer SystemsApr 24Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User ProxiesMicrosoft · arXiv (Cornell University)1 citationApr 23Scoop: Mitigation of Recapture Attacks on Provenance-Based Media AuthenticationMicrosoft · GetMobile Mobile Computing and Communications1 citationApr 23Removing Sandbagging in LLMs by Training with Weak SupervisionAnthropic · arXiv (Cornell University)Apr 23CI-Work: Benchmarking Contextual Integrity in Enterprise LLM AgentsMicrosoft · arXiv (Cornell University)Apr 23ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMsAlibaba · arXiv (Cornell University)Apr 23AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool UseAlibaba · arXiv (Cornell University)Apr 23AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool UseAlibaba · arXiv (Cornell University)Apr 23CI-Work: Benchmarking Contextual Integrity in Enterprise LLM AgentsMicrosoft · arXiv (Cornell University)Apr 23Quotient-Space Diffusion ModelsMicrosoft · arXiv (Cornell University)Apr 23ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMsAlibaba · arXiv (Cornell University)Apr 23Position Paper: Denial-of-Service against Multi-Round Transaction SimulationMicrosoft · arXiv (Cornell University)Apr 23Language as a Latent Variable for Reasoning OptimizationAlibaba · arXiv (Cornell University)Apr 23The Impact of Memory Configuration on Server EfficiencyMicrosoft · ACM/SPEC International Conference on Performance Engineering (ICPE)Apr 23WordCon: Word-Level Typography Control in Visual Text RenderingAlibaba · IEEE Transactions on Circuits and Systems for Video TechnologyApr 23Output-Optimal Evaluation of Conjunctive QueriesMicrosoft · ACM SIGMOD RecordApr 23Energy Efficiency Benchmarking of GPU Servers - Why It's Challenging, What Matters, and How to Do It RightMicrosoft, NVIDIA · ACM/SPEC International Conference on Performance Engineering (ICPE)Apr 23SPEC Efficiency Benchmarks - Achievements and ProspectsMicrosoft, NVIDIA · ACM/SPEC International Conference on Performance Engineering (ICPE)Apr 23Clinical Knowledge-Guided PET/CT Lesion Segmentation With Interpretable Fusion of Metabolic and Structural CuesAlibaba · IEEE Transactions on Medical ImagingApr 23Beyond Microservices: Testing Web-Scale RCA Methods on GPU-Driven LLM WorkloadsTechnology Innovation Institute · ACM/SPEC International Conference on Performance Engineering (ICPE)Apr 23Evaluating large language models for accuracy incentivizes hallucinationsOpenAI · Nature24 citationsApr 22