Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Adaptively Robust Resettable StreamingAlphabet · arXiv (Cornell University)Jan 29Noisy Pairwise-Comparison Random Search for Smooth Nonconvex OptimizationGoogle DeepMind · arXiv (Cornell University)Jan 29ECO: Quantized Training without Full-Precision Master WeightsAlphabet · arXiv (Cornell University)Jan 29Comparative Evaluation of Deep Learning Architectures for Human Action RecognitionMeta · Computer Fraud & SecurityJan 29A benchmark of expert-level academic questions to assess AI capabilitiesAlphabet, Anthropic, Cohere, Google DeepMind, Microsoft, OpenAI · Nature185 citationsJan 28Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question ReformulationAlibaba · arXiv (Cornell University)6 citationsJan 28DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research AgentsAlphabet · arXiv (Cornell University)3 citationsJan 28Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern TransformersAlphabet · arXiv (Cornell University)2 citationsJan 28Hallucination Begins Where Saliency DropsAlibaba · arXiv (Cornell University)2 citationsJan 28Efficient Autoregressive Video Diffusion with Dummy HeadMicrosoft · arXiv (Cornell University)2 citationsJan 28$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ RetrievalNVIDIA · arXiv (Cornell University)2 citationsJan 28EduYOLO: A classroom behavior recognition framework based on high-resolution feature attention fusioniFlytek · Expert Systems with Applications2 citationsJan 28MACHINE LEARNING FOR NETWORK INTRUSION DETECTION IN USA CRITICAL INFRASTRUCTURE: CHALLENGES AND OPPORTUNITIESMeta · International Journal of Network Security & Its Applications1 citationJan 28Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image ModelsAlibaba · arXiv (Cornell University)1 citationJan 28What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answeringGoogle DeepMind · arXiv (Cornell University)1 citationJan 28DenseGRPO: From Sparse to Dense Reward for Flow Matching Model AlignmentAlibaba · arXiv (Cornell University)1 citationJan 28MetaAttention: A Unified and Performant Attention Framework across Hardware BackendsMicrosoft · ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming1 citationJan 28CXLock: Efficient and Scalable Lock Management for CXL-Enabled Distributed SystemsAlibaba · IEEE Transactions on Computers1 citationJan 28It’s about Time: Temporal Abstractions for Asynchronous GPU Tensor ComputationsNVIDIA · ACM SIGPLAN International Conference on Compiler Construction (CC)1 citationJan 28Cacheman: A Comprehensive Last-Level Cache Management System for Multi-tenant CloudsAlibaba · ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming1 citationJan 28Predicting Adaptively Chosen Observables in Quantum SystemsAlphabet · PRX Quantum1 citationJan 28PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMsAlphabet · arXiv (Cornell University)Jan 28A Theory of Universal Agnostic LearningAlphabet · arXiv (Cornell University)Jan 28CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified CriteriaAlibaba · arXiv (Cornell University)Jan 28SERA: Soft-Verified Efficient Repository AgentsAllen Institute for AI · arXiv (Cornell University)Jan 28