Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language ModelsAlphabet · arXiv (Cornell University)May 17Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning ModelsAlphabet · arXiv (Cornell University)May 17Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided PruningAlphabet · arXiv (Cornell University)May 17Leveraging LLMs and social media to understand user perception of smartphone-based earthquake early warningsAlphabet · Scientific ReportsMay 16MedASR: An Open-Source Model for High-Accuracy Medical DictationAlphabet · arXiv (Cornell University)May 15ITHICA: Intra-Thread Instruction Checking Approach for Defect-Induced Silent Data CorruptionsAlphabet · arXiv (Cornell University)May 153D Segmentation Using Viewpoint-Dependent Spatial RelationshipsAlphabet · arXiv (Cornell University)May 15Efficient quantum algorithm for linear matrix differential equations and applications to open quantum systemsAlphabet · arXiv (Cornell University)May 15Quantum Solvers for Nonlinear Matrix Equations in Quantum ChemistryAlphabet · arXiv (Cornell University)May 15ITHICA: Intra-Thread Instruction Checking Approach for Defect-Induced Silent Data CorruptionsAlphabet · arXiv (Cornell University)May 15S$^{2}$VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame MatrixAlphabet · IEEE Transactions on Pattern Analysis and Machine Intelligence1 citationMay 14Polynomial Histograms for Memory-Efficient Representation of Long-tailed System DistributionsAlphabet · arXiv (Cornell University)May 14Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of ExperienceAlphabet · arXiv (Cornell University)May 14NodeSynth: Socially Aligned Synthetic Data for AI EvaluationAlphabet · arXiv (Cornell University)May 14Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUsGoogle DeepMind · arXiv (Cornell University)May 14LiSA: Lifelong Safety Adaptation via Conservative Policy InductionAlphabet · arXiv (Cornell University)May 14SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context InferenceAlphabet · arXiv (Cornell University)May 13SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context InferenceAlphabet · arXiv (Cornell University)May 13Stochastic Matching via Local SparsificationAlphabet · arXiv (Cornell University)May 13What is Learnable in Valiant's Theory of the Learnable?Alphabet · arXiv (Cornell University)May 13Context Training with Active Information SeekingGoogle DeepMind · arXiv (Cornell University)May 13Scale-Sensitive Shattering: Learnability and Evaluability at Optimal ScaleAlphabet · arXiv (Cornell University)May 13What You Read Is What You Classify: Highlighting Attributions to Text and Text-like InputsGoogle DeepMind · AIMay 13TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D TrackingGoogle DeepMind · arXiv (Cornell University)May 12Sobolev Regularized MMD Gradient FlowAlphabet, Google DeepMind · arXiv (Cornell University)May 12