Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
ReSolve: Reusing Candidate Reasoning through Selective Generative ModerationAlphabet · arXiv (Cornell University)Oct 1Bridging Machine Learning and Algorithmic Information Theory, Part VII: Algorithmic Information Kernels and Kernel Discrepancies on Countable SpacesGoogle DeepMind · EntropyOct 1Provably Lossless Acceleration of DNN Mutation Testing via MemoizationAlphabet · Proceedings of the ACM on software engineering.Oct 1Automated Modernization of Machine Learning Engineering Notebooks for ReproducibilityAlphabet · Proceedings of the ACM on software engineering.Oct 1Bayesian Nonparametric Risk Assessment in Developmental Toxicity Studies With Ordinal ResponsesAlphabet · EnvironmetricsOct 1Polynomial-Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label SettingGoogle DeepMind, Technology Innovation Institute · Journal of CryptologyOct 1Function-preserving watermarking of AI-generated proteinsGoogle DeepMind · Nature2 citationsSep 30ContextFidelity-Bench: A Three-Paradigm Framework for Evaluating Multi-Turn Hallucination Behavior in Language ModelsAlphabet · BenchCouncil Transactions on Benchmarks Standards and EvaluationsSep 30Quantum Algorithms for OPI Variants Beyond Locality and Classical DecodabilityAlphabet · arXiv (Cornell University)Sep 30Decoupling of the QAOA into independent spin-boson systems and high-depth performance on pure and mixed spin glassesAlphabet · arXiv (Cornell University)Sep 30Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow MapsGoogle DeepMind · arXiv (Cornell University)Sep 30A Fourier-Label Information-Loss Barrier for Dihedral Coset AlgorithmsAlphabet · arXiv (Cornell University)Sep 30Gibbs Sampling in the Shattered Phase by Decoded Quantum InterferometryAlphabet · arXiv (Cornell University)Sep 30Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure DiagnosisAlphabet · arXiv (Cornell University)Sep 30OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and ReasoningAlphabet · arXiv (Cornell University)Sep 30Cycle Codes and Decoded Quantum InterferometryAlphabet · arXiv (Cornell University)Sep 30Aligning Thoughts with Answers: Probability Rewards to Tame Thinking DriftGoogle DeepMind · arXiv (Cornell University)Sep 30Cogentic: Multi-Agent Orchestration for Automated Proof DiscoveryAlphabet · arXiv (Cornell University)Sep 30dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM ScaleAlphabet · arXiv (Cornell University)Sep 30Provable Classical and Quantum Local Algorithms for Max-$k$-Cut and Quantum Advantage at Moderate GirthAlphabet · arXiv (Cornell University)Sep 30Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting CodesAlphabet · arXiv (Cornell University)Sep 30Mathematical discovery and exploration can be done at scaleGoogle DeepMind · Proceedings of the National Academy of SciencesSep 30Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before AnsweringAlphabet · arXiv (Cornell University)Sep 29AIM: Agentic Idea Management for Automated ResearchAlphabet · arXiv (Cornell University)Sep 29Conditional Generation of Creative Chess Puzzles with Diffusion ModelsGoogle DeepMind · arXiv (Cornell University)Sep 29