Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
From Complexity to Clarity: A Case Study in Revenue System TransformationAlphabet · Technix International Journal for Engineering ResearchJan 1, 2025LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMsAlphabet · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)Jan 1, 2025An empirical study of validating synthetic data for formula generationAlphabet, Microsoft · Findings of the Association for Computational Linguistics: NAACLJan 1, 2025Keep Guessing? When Considering Inference Scaling, Mind the BaselinesAlphabet, Google DeepMind · Findings of the Association for Computational Linguistics: NAACLJan 1, 2025Breaking Down Power Barriers in On-Device Streaming ASR: Insights and SolutionsAlphabet · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)Jan 1, 2025A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in NewswritingAlphabet · International Workshop on Knowledge-Augmented Methods for Natural Language Processing (KnowledgeNLP)Jan 1, 2025Chasing Random: Instruction Selection Strategies Fail to GeneralizeAlphabet, Google DeepMind · Findings of the Association for Computational Linguistics: NAACLJan 1, 2025Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts?Google DeepMind · Findings of the Association for Computational Linguistics: NAACLJan 1, 2025Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-TuningGoogle DeepMind · neural information processing systemsJan 1, 2025Scaling ML Workloads with Google’s Evolving Datacenter Network ArchitectureAlphabet · Optical Fiber Communication ConferenceJan 1, 2025Self-masking Networks for Unsupervised AdaptationAlphabet · Lecture notes in computer scienceJan 1, 2025KEIR @ ECIR 2025: The Second Workshop on Knowledge-Enhanced Information RetrievalAlphabet · Lecture notes in computer scienceJan 1, 2025Dike: Quantitatively and Accurately Gauge the Exploitability of Speculative GadgetsAlphabet · Network and Distributed System Security SymposiumJan 1, 2025A Combinatorial View of Holant Problems on Higher DomainsAlphabet · Lecture notes in computer scienceJan 1, 2025Dimension-free Score Matching and Time Bootstrapping for Diffusion ModelsGoogle DeepMind · neural information processing systemsJan 1, 2025On Agnostic PAC Learning in the Small Error RegimeAlphabet · neural information processing systemsJan 1, 2025Escaping Collapse: The Strength of Weak Data for Large Language Model TrainingAlphabet · neural information processing systemsJan 1, 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM SystemsAlphabet · neural information processing systemsJan 1, 2025Analyzing Similarity Metrics for Data Selection for Language Model PretrainingAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025Scaling Embedding Layers in Language ModelsAlphabet · neural information processing systemsJan 1, 2025Differentiable Approximations for Distance QueriesAlphabet · Society for Industrial and Applied Mathematics eBooksJan 1, 2025A Tight VC-Dimension Analysis of Clustering Coresets with ApplicationsAlphabet · Society for Industrial and Applied Mathematics eBooksJan 1, 20253D Interaction Geometric Pre-training for Molecular Relational LearningGoogle DeepMind · neural information processing systemsJan 1, 2025Fast Training of Large Kernel Models with Delayed ProjectionsAlphabet · neural information processing systemsJan 1, 2025Probably Approximately Precision and Recall LearningAlphabet · neural information processing systemsJan 1, 2025