Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML DatasetsAlphabet · arXiv (Cornell University)Oct 5Neural Fields Encode Adaptation GeometrySakana AI · arXiv (Cornell University)Oct 5Activation Denoising: A Robustness View on Parallel vs Sequential LLM QuantizationMicrosoft · arXiv (Cornell University)Oct 5Exact Unlearning via Quantized Sufficient StatisticsMeta · arXiv (Cornell University)Oct 5Logbook: Extremely Long-form Audio Event UnderstandingMeta · arXiv (Cornell University)Oct 5NCCL M2N: A Layout- and Topology-Aware Collective for Distributed Tensor ReshardingNVIDIA · arXiv (Cornell University)Oct 5Ofan: Optimal Load Balancing for AI TrainingNVIDIA · arXiv (Cornell University)Oct 5Fork-and-Flush: Escaping Idea Basins in Autoresearch AgentsMicrosoft · arXiv (Cornell University)Oct 5Base Models Can Reason By Taking a Cue From Training DataAllen Institute for AI · arXiv (Cornell University)Oct 5Improved Sublinear Algorithms for Maximal Independent Set and Metric Steiner ForestMicrosoft · arXiv (Cornell University)Oct 5Mining Agent Skills from Production TracesMicrosoft · arXiv (Cornell University)Oct 5Considering Context: When World Models Need Context EncodersMicrosoft · arXiv (Cornell University)Oct 5A Mixed-Precision Model for Matrix-Splitting MethodsNVIDIA · arXiv (Cornell University)Oct 5GraphDecisionBench: Benchmarking System One Models on Graph TasksMicrosoft · arXiv (Cornell University)Oct 5Qubit CSS codes with Universal Transversal GatesNVIDIA · arXiv (Cornell University)Oct 5Protocol-Sensitive Evaluation of Log Anomaly Detection: Component Costs and Target-Access Sensitivity on HDFS and BGLAlphabet · arXiv (Cornell University)Oct 5Bounded Provisional Visibility: Controlling Poisoning Exposure in Continuously Ingested RAG Vector StoresAlphabet · arXiv (Cornell University)Oct 5Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design VerificationAlphabet · arXiv (Cornell University)Oct 5BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding ModelsAlphabet · arXiv (Cornell University)Oct 5AuraSE: Low-Hallucination Generative Speech Enhancement via Multimodal Flow Matching and Inference Policy OptimizationMicrosoft · arXiv (Cornell University)Oct 5Streaming Regev's Quantum Factoring AlgorithmAlphabet · arXiv (Cornell University)Oct 5Capability-Driven Self-Evolution of Agent MemoryMicrosoft · arXiv (Cornell University)Oct 5RESOLVE: Language-Agnostic Validation of GPU Kernels Through Testing, Reduction, and ProofMicrosoft · arXiv (Cornell University)Oct 5RAISED: Self-Distillation for Robustness to Prompt Injection in LLM AgentsGoogle DeepMind · arXiv (Cornell University)Oct 5Learning What to Imitate: Entropy-Aware Distribution MixingAllen Institute for AI · arXiv (Cornell University)Oct 5