Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Test-Time Optimization of Query Embeddings with Ranking Aware Reward MaximizationGoogle DeepMind · arXiv (Cornell University)Aug 12Sci-Surf: Navigating Scientific Literature Discovery through Human Feedback and Intelligent SummarizationAlphabet · arXiv (Cornell University)Aug 12Gaze Target Estimation Anywhere with ConceptsAlphabet · arXiv (Cornell University)Aug 11Graphic Matroid Secretary without the GraphAlphabet · arXiv (Cornell University)Aug 11VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and TranslationGoogle DeepMind · arXiv (Cornell University)Aug 11Performance and user response of android’s smartphone-based alerts in the 2025 Marmara Ereğlisi earthquakeAlphabet · Nature CommunicationsAug 11HERMES: Repurposing User-Driven Speed Tests to Monitor the InternetAlphabet · ACM SIGCOMM Conference (SIGCOMM)Aug 11Toward WAN-Aware LLM Training Across Heterogeneous, Geo-Distributed SitesAlphabet · ACM SIGCOMM Conference (SIGCOMM)Aug 11GGN: Experiences in Designing and Deploying the Next-Generation Google Global NetworkAlphabet · ACM SIGCOMM Conference (SIGCOMM)Aug 11CSIG: Congestion Signaling for Datacenter TransportsAlphabet · ACM SIGCOMM Conference (SIGCOMM)Aug 11Performance and user response of android's smartphone-based alerts in the 2025 Marmara Ereğlisi earthquake.Alphabet · PubMedAug 11AI Query Compilation for Unified and Optimized ExecutionAlphabet · arXiv (Cornell University)Aug 10ArchAgent v2: A Case Study with the Data Prefetching ChampionshipGoogle DeepMind · arXiv (Cornell University)Aug 10Unitary Synthesis with Fewer T GatesAlphabet · PRX QuantumAug 10Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific MethodsAlphabet · arXiv (Cornell University)Aug 9V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous ControlGoogle DeepMind · arXiv (Cornell University)Aug 8Human learning of probability distributions is biased toward moderate structural complexityGoogle DeepMind · Nature CommunicationsAug 8WebRider: Persona-Conditioned Intent Controllers for Live-Web AssistanceAlphabet · arXiv (Cornell University)Aug 71st Workshop on AI for Fraud and AbuseAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 75th Workshop on End-End Customer Journey OptimizationAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 7PiPNN: Ultra-Scalable Graph-Based Nearest Neighbor IndexingAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)4 citationsAug 6Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective AlignmentAlphabet · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)1 citationAug 6A Near-Optimal Lower Bound for Prefix-Matrix FactorizationsAlphabet · arXiv (Cornell University)Aug 6Characterizing the Quality Profile of AI-Generated C++ in ProductionAlphabet · arXiv (Cornell University)Aug 6Retrofitting Linear Attention into Diffusion Language ModelsGoogle DeepMind · arXiv (Cornell University)Aug 6