Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Language models transmit behavioural traits through hidden signals in dataAnthropic · Nature9 citationsApr 15Extended User Interrupts (xUI): Fast and Flexible User-Space Notification for x86 and RISC-VAlphabet · ACM Transactions on Computer Systems1 citationApr 15Filament: Denning-Style Information Flow Control for RustAlphabet · arXiv (Cornell University)Apr 15Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context AdaptationMicrosoft · arXiv (Cornell University)Apr 15Improving Human Performance with Value-Aware Interventions: A Case Study in ChessMicrosoft · arXiv (Cornell University)Apr 15Distributed Variational Quantum Linear SolverNVIDIA · arXiv (Cornell University)Apr 15How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source DataHugging Face · arXiv (Cornell University)Apr 15Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language ModelsNVIDIA · arXiv (Cornell University)Apr 15Don't Let AI Agents YOLO Your Files: Information and Control in Agent-Native FilesystemsMicrosoft · arXiv (Cornell University)Apr 15DUET: Joint Exploration of User Item Profiles in Recommendation SystemMicrosoft · arXiv (Cornell University)Apr 15Enhancing Mixture-of-Experts Specialization via Cluster-Aware UpcyclingLG AI Research · arXiv (Cornell University)Apr 15Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed DataMicrosoft · arXiv (Cornell University)Apr 15Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic ArchitecturesMicrosoft · arXiv (Cornell University)Apr 15Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient InferenceAlibaba · arXiv (Cornell University)Apr 15Stochastic Pairwise MIS for Unbiased Large‐Kernel Reuse in Real‐TimeNVIDIA · Computer Graphics Forum2 citationsApr 14RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache EvictionAlibaba · arXiv (Cornell University)Apr 14Better and Worse with Scale: How Contextual Entrainment Diverges with Model SizeNVIDIA · arXiv (Cornell University)Apr 14Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AIMicrosoft · arXiv (Cornell University)Apr 14Event Tensor: A Unified Abstraction for Compiling Dynamic MegakernelNVIDIA · arXiv (Cornell University)Apr 14Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation ModelsMicrosoft · arXiv (Cornell University)Apr 14Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level OptimizationMeta · arXiv (Cornell University)Apr 14QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical IntelligenceAlibaba · arXiv (Cornell University)Apr 14Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving DescentAlphabet · arXiv (Cornell University)Apr 14Fast and accurate AI-based pre-decoders for surface codesNVIDIA · arXiv (Cornell University)Apr 14PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement LearningAlibaba · arXiv (Cornell University)Apr 14