Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Representation-Based Exploration for Language Models: From Test-Time to Post-TrainingMicrosoft · arXiv (Cornell University)16 citationsOct 13, 2025Asking Clarifying Questions for Preference Elicitation With Large Language ModelsAlphabet · arXiv (Cornell University)14 citationsOct 13, 2025GAR: Generative Adversarial Reinforcement Learning for Formal Theorem ProvingNVIDIA · arXiv (Cornell University)6 citationsOct 13, 2025Qiboml: towards the orchestration of quantum-classical machine learningTechnology Innovation Institute · arXiv (Cornell University)6 citationsOct 13, 2025AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language ModelsMicrosoft · arXiv (Cornell University)5 citationsOct 13, 2025Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning ModelsMicrosoft · arXiv (Cornell University)3 citationsOct 13, 2025Universal and Quality-Preserving Watermark Removal Based on Unpaired LearningAlibaba · IEEE Transactions on Dependable and Secure Computing3 citationsOct 13, 2025Enhancing the Performance and Speed of Quantum Support Vector Classifier via Neural Quantum Embedding and Tensor NetworkNVIDIA · International Conference on Artificial Intelligence for Medicine, Health and Care (AIxMHC)1 citationOct 13, 2025Exposing and Mitigating Adversarial AI Threats in IoT/5G Intrusion Detection Systems Using Random Forest and Feature ReductionAlphabet · IEEE International Carnahan Conference on Security Technology (ICCST)Oct 13, 2025FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMsNVIDIA · arXiv (Cornell University)Oct 13, 2025BlackIce: A Containerized Red Teaming Toolkit for AI Security TestingDatabricks · arXiv (Cornell University)Oct 13, 2025LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph EmbeddingsAlibaba · arXiv (Cornell University)Oct 13, 2025Stable and Fault-Tolerant Decentralized Traffic EngineeringMicrosoft · arXiv (Cornell University)Oct 13, 2025Tracing the Traces: Latent Temporal Signals for Efficient and Accurate ReasoningMicrosoft, NVIDIA · arXiv (Cornell University)9 citationsOct 12, 2025Source Separation by Flow MatchingGoogle DeepMind · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)5 citationsOct 12, 2025EdgeReasoning: Characterizing Reasoning LLM Deployment on Edge GPUsNVIDIA · IEEE International Symposium on Workload Characterization4 citationsOct 12, 2025Beyond Sound: The First Workshop on Intelligent Acoustic Sensing on WearablesAlphabet · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp)1 citationOct 12, 2025miniGiraffe: A Pangenomic Mapping Proxy AppMicrosoft · IEEE International Symposium on Workload Characterization1 citationOct 12, 2025Scene-wide Acoustic Parameter EstimationMeta · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)1 citationOct 12, 2025Controlling the Parameterized Multi-channel Wiener Filter using a tiny neural networkMeta · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)1 citationOct 12, 2025Distributed Asynchronous Device Speech Enhancement via Windowed Cross-AttentionMicrosoft · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)1 citationOct 12, 2025Exploring MRAM for On-Chip Texture Storage in Rendering ApplicationsMeta · IFIP/IEEE International Conference on Very Large Scale IntegrationOct 12, 2025Foscu: Feasibility of Synthetic Mri Generation Via Duo-Diffusion Models for Enhancement of 3D U-Nets in Hepatic SegmentationNVIDIA · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)Oct 12, 2025BetterTogether: An Interference-Aware Framework for Fine-grained Software Pipelining on Heterogeneous SoCsMicrosoft · IEEE International Symposium on Workload CharacterizationOct 12, 2025From image to report: automating lung cancer screening interpretation and reporting with vision-language modelsNVIDIA · Journal of Biomedical Informatics6 citationsOct 11, 2025