Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Teaching LLMs to Hear Who Spoke What: Metadata-Supervised Pretraining for Encoder-Free Speech-LLMsMicrosoft · arXiv (Cornell University)Oct 1Serving a Revisable World: Versioned Execution for Interruptible AgentsNVIDIA · arXiv (Cornell University)Oct 1ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New ResearchAllen Institute for AI · arXiv (Cornell University)Oct 1CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space TransformationsNVIDIA · arXiv (Cornell University)Oct 1RMS-AQA: A Two-Stage Spatial Audio Question Answering Benchmark for Real-World Domestic EnvironmentsNVIDIA · arXiv (Cornell University)Oct 1VeriHarness: Scaling Agentic Verification for Long-Horizon TasksAlphabet · arXiv (Cornell University)Oct 1How the Audit Rule Shapes Faithful Factor Explanations in LLMsAlibaba · arXiv (Cornell University)Oct 1LESS: Lightweight Evolutionary Supernet Search in MinutesSakana AI · arXiv (Cornell University)Oct 1Who Thinks First? Designing Productive Friction with Engage-to-Unlock GenAIAlphabet, Google DeepMind · arXiv (Cornell University)Oct 1Learning Rate Transfer for Hybrid Transformer-SSM ArchitecturesLG AI Research · arXiv (Cornell University)Oct 1LAST: Looped Audio Spectrogram TransformerGoogle DeepMind · arXiv (Cornell University)Oct 1OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling AgentsAlibaba · arXiv (Cornell University)Oct 1Old Ideas, Novel Problems: The Instability of LLM-Based Novelty EvaluationAllen Institute for AI, Microsoft · arXiv (Cornell University)Oct 1My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement LearningAlibaba · arXiv (Cornell University)Oct 1ReSolve: Reusing Candidate Reasoning through Selective Generative ModerationAlphabet · arXiv (Cornell University)Oct 1VETO: Video Efficient Token Optimization for Vision Language ModelsNVIDIA · arXiv (Cornell University)Oct 1Optimizing Effective Training Time for Large-Scale Recommendation SystemsMeta · arXiv (Cornell University)Oct 1Bridging Machine Learning and Algorithmic Information Theory, Part VII: Algorithmic Information Kernels and Kernel Discrepancies on Countable SpacesGoogle DeepMind · EntropyOct 1Predicting perceptual discriminability of room impulse responses at similar source–receiver distances using optimal transportMeta · JASA Express LettersOct 1CREST: Chemical Reaction Extraction from Scientific TextsiFlytek · Journal on Image and Video ProcessingOct 1Tracking Borrows with Regular ExpressionsMicrosoft · Proceedings of the ACM on Programming LanguagesOct 1How Does Killing Surviving Mutants Help Detect Real Bugs with Assertion Generation? A Controlled ExperimentMicrosoft · Proceedings of the ACM on software engineering.Oct 1Agents as Software: A Programming Languages Agenda for Agent ReliabilityMicrosoft · ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software (Onward!)Oct 1FlowLog: Re-thinking Datalog for Fast and Extensible Static AnalysisMicrosoft · ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH)Oct 1Provably Lossless Acceleration of DNN Mutation Testing via MemoizationAlphabet · Proceedings of the ACM on software engineering.Oct 1