Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Decoupling the components of geometric understanding in Vision Language ModelsAlphabet · arXiv (Cornell University)4 citationsMar 5, 2025Robust Learning of Diverse Code EditsMicrosoft · arXiv (Cornell University)4 citationsMar 5, 2025KnapsackLB: Enabling Performance-Aware Layer-4 Load BalancingMicrosoft · Proceedings of the ACM on Networking4 citationsMar 5, 2025Model Behavior Specification by Leveraging LLM Self-Playing and Self-ImprovingAlphabet · arXiv (Cornell University)2 citationsMar 5, 2025It's My Data Too: Private ML for Datasets with Multi-User Training ExamplesAlphabet, Google DeepMind · arXiv (Cornell University)2 citationsMar 5, 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024Allen Institute for AI · arXiv (Cornell University)101 citationsMar 4, 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of ExpertsGoogle DeepMind · arXiv (Cornell University)55 citationsMar 4, 2025Building Your Own Product Copilot: Challenges, Opportunities, and NeedsMicrosoft · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)43 citationsMar 4, 2025Stability of Classical Shadows under Gate-Dependent NoiseTechnology Innovation Institute · Physical Review Letters18 citationsMar 4, 2025Weak-to-Strong Generalization Even in Random Feature Networks, ProvablyMicrosoft · arXiv (Cornell University)14 citationsMar 4, 2025AIOpsArena: Scenario-Oriented Evaluation and Leaderboard for AIOps Algorithms in MicroservicesMicrosoft · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)9 citationsMar 4, 2025Go Beyond Your Means: Unlearning with Per-Sample Gradient OrthogonalizationNVIDIA · arXiv (Cornell University)8 citationsMar 4, 2025Constant time lattice reduction in dimension 4 with application to SQIsignTechnology Innovation Institute · IACR Transactions on Cryptographic Hardware and Embedded Systems3 citationsMar 4, 2025Is Bellman Equation Enough for Learning Control?Microsoft · arXiv (Cornell University)2 citationsMar 4, 2025Teaching Metric Distance to Discrete Autoregressive Language ModelsLG AI Research · arXiv (Cornell University)2 citationsMar 4, 2025Experience Replay with Random ReshufflingPreferred Networks · arXiv (Cornell University)2 citationsMar 4, 2025Forecasting Graph-Based Time-Dependent Data with Graph Sequence AttentionMicrosoft · ACM Transactions on Knowledge Discovery from Data1 citationMar 4, 2025DragonRadar: Fuzzing Linux Kernel Deployed in Cloud-Native EnvironmentAlibaba · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)Mar 4, 2025Large-Scale Data Selection for Instruction TuningAllen Institute for AI · arXiv (Cornell University)45 citationsMar 3, 2025LaMD: Latent Motion Diffusion for Image-Conditional Video GenerationMicrosoft · International Journal of Computer Vision40 citationsMar 3, 2025Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative ModelsAlibaba · arXiv (Cornell University)23 citationsMar 3, 2025Advancing vision-language models in front-end development via data synthesisAlibaba · arXiv (Cornell University)17 citationsMar 3, 2025One ruler to measure them all: Benchmarking multilingual long-context language modelsMicrosoft · arXiv (Cornell University)16 citationsMar 3, 2025Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced SettingCerebras Systems · arXiv (Cornell University)16 citationsMar 3, 2025GlossyGS: Inverse Rendering of Glossy Objects With 3D Gaussian SplattingAlibaba · IEEE Transactions on Visualization and Computer Graphics16 citationsMar 3, 2025