Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MVEB: Massive Video Embedding BenchmarkAlphabet · arXiv (Cornell University)Jun 12A theoretical model for task routing in mixture-of-expert transformersAlphabet · arXiv (Cornell University)Jun 12An Efficient Private Algorithm for Community DetectionAlphabet · arXiv (Cornell University)Jun 12Compass vs Railway Tracks: Unpacking User Mental Models for Communicating Long-Horizon Work to Humans vs. AIAlphabet · Designing Interactive Systems ConferenceJun 12Gefen: Optimized Stochastic OptimizerAlphabet · arXiv (Cornell University)Jun 11TASR: Training-Free Adaptive Stopping for Iterative RetrievalAlphabet · arXiv (Cornell University)Jun 11Rethinking the UI of GenUI: A Tale of Two DesignsAlphabet · arXiv (Cornell University)Jun 11Accelerating Speculative Diffusions via Block VerificationAlphabet · arXiv (Cornell University)Jun 11DeduBB: Binary Code Size Reduction via Post-Link Basic Block DeduplicationAlphabet · ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES)Jun 11PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt InjectionsAlphabet · arXiv (Cornell University)Jun 10Efficient Quantum Hermite TransformAlphabet · ACM Symposium on Theory of Computing (STOC)2 citationsJun 9No Exponential Quantum Speedup for SIS∞ AnymoreAlphabet · ACM Symposium on Theory of Computing (STOC)1 citationJun 9Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization SensitivityAlphabet · arXiv (Cornell University)Jun 9Benchmarking and Exploring the Capabilities of LLMs for Attack InvestigationsAlphabet · arXiv (Cornell University)Jun 9CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMsGoogle DeepMind · arXiv (Cornell University)Jun 9Advancing the State-of-the-Art in Empirical Privacy AuditingAlphabet · arXiv (Cornell University)Jun 9Combinatorial Optimization using Comparison OraclesAlphabet · ACM Symposium on Theory of Computing (STOC)Jun 9Near-Optimal Directed Euclidean Spanners in High DimensionsAlphabet · ACM Symposium on Theory of Computing (STOC)Jun 9A (4+ϵ)-Approximation for Euclidean k-Means via Non-monotone Dual-FittingAlphabet · ACM Symposium on Theory of Computing (STOC)Jun 9A Strong Linear Programming Relaxation for Weighted Tree AugmentationAlphabet · ACM Symposium on Theory of Computing (STOC)Jun 9Breaking Barriers for Distributed MIS by Faster Degree ReductionAlphabet · ACM Symposium on Theory of Computing (STOC)Jun 9How AI is reshaping discovery in maths and physicsGoogle DeepMind · Nature1 citationJun 8NEURA: A Unified and Retargetable Compilation Framework for Coarse-Grained Reconfigurable ArchitecturesAlphabet · Proceedings of the ACM on Programming Languages1 citationJun 8Difference-Aware Retrieval Policies for Imitation LearningGoogle DeepMind · arXiv (Cornell University)Jun 8Analyzing Bytes: Pre-Disassembly Static Binary AnalysisAlphabet · Proceedings of the ACM on Programming LanguagesJun 8