Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SA-SSL-MOS: Self-supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech AssessmentAlphabet · 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 16Privacy-preserved LLM Cascade via CoT-enhanced Policy LearningAlphabet · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16Third Workshop on Generative AI for Recommender Systems and PersonalizationAlphabet, Databricks · ACM International Conference on Web Search and Data Mining (WSDM)Feb 16Simplicity and Complexity in Combinatorial OptimizationGoogle DeepMind · Entropy1 citationFeb 15Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric FactualityAlphabet · arXiv (Cornell University)Feb 15TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series ReasoningAlphabet · arXiv (Cornell University)Feb 15Bridging the Urban Divide: Adaptive Cross-City Learning for Disaster Sentiment UnderstandingAlphabet · arXiv (Cornell University)Feb 15SWING: Unlocking Implicit Graph Representations for Graph Random FeaturesAlphabet · arXiv (Cornell University)Feb 13Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party NegotiationAlphabet · arXiv (Cornell University)Feb 12Keeping a Secret Requires a Good Memory: Space Lower-Bounds for Private AlgorithmsAlphabet · arXiv (Cornell University)Feb 12Chamfer-Linkage for Hierarchical Agglomerative ClusteringAlphabet · arXiv (Cornell University)Feb 11Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier GuidanceAlphabet · arXiv (Cornell University)Feb 10Adaptive Optimization via Momentum on Variance-Normalized GradientsAlphabet · arXiv (Cornell University)Feb 10AI-Assisted Scientific Assessment: A Case Study on Climate ChangeGoogle DeepMind · arXiv (Cornell University)Feb 10Step-resolved data attribution for looped transformersGoogle DeepMind · arXiv (Cornell University)Feb 10Evaluating CS1-LLM: Integrating LLMs and Examining Student Outcomes in an Introductory Computer Science CourseAlphabet · Australasian Computing Education Conference2 citationsFeb 9Reduction of Cyber Risk in Internet of Things Healthcare Systems: Ensuring Patient Data During Transmission and Pairing with Secure DevicesAlphabet · International Conference on Communication, Computing and Emerging Technologies (IC3ET)Feb 9The Price of Privacy For Approximating Max-CSPAlphabet · arXiv (Cornell University)Feb 9Stress-Testing Alignment Audits With Prompt-Level Strategic DeceptionAlphabet, Google DeepMind · arXiv (Cornell University)Feb 9CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time ComputeGoogle DeepMind · arXiv (Cornell University)Feb 9CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal AttributionAlphabet, Google DeepMind · arXiv (Cornell University)Feb 8Rational TransductorsAlphabet · arXiv (Cornell University)Feb 7Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image GenerationAlphabet, Google DeepMind · arXiv (Cornell University)Feb 6Statistical Learning from Attribution SetsAlphabet · arXiv (Cornell University)Feb 6