Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchGoogle DeepMind, Meta · neural information processing systems1 citationJan 1, 2025Distillation Robustifies UnlearningAnthropic, Google DeepMind · neural information processing systems1 citationJan 1, 2025MLE-STAR: Machine Learning Engineering Agent via Search and Targeted RefinementAlphabet · neural information processing systems1 citationJan 1, 2025Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point IterationsGoogle DeepMind · neural information processing systems1 citationJan 1, 2025Simulating Society Requires Simulating ThoughtAlphabet · neural information processing systems1 citationJan 1, 2025What Really is a Member? Discrediting Membership Inference via PoisoningGoogle DeepMind · neural information processing systems1 citationJan 1, 2025Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch MiningAlphabet · neural information processing systems1 citationJan 1, 2025Equivariance Everywhere All At Once: A Recipe for Graph Foundation ModelsAlphabet · neural information processing systems1 citationJan 1, 2025Regularized least squares learning with heavy-tailed noise is minimax optimalGoogle DeepMind · neural information processing systems1 citationJan 1, 2025Single-pass Adaptive Image Tokenization for Minimum Program SearchAlphabet · neural information processing systems1 citationJan 1, 2025Zero-Shot Context Generalization in Reinforcement Learning from Few Training ContextsAlphabet · neural information processing systems1 citationJan 1, 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and TriggersAlphabet · neural information processing systems1 citationJan 1, 2025FlexOLMo: Open Language Models for Flexible Data UseAllen Institute for AI, Alphabet · neural information processing systems1 citationJan 1, 2025Private Hyperparameter Tuning with Ex-Post GuaranteeAlphabet · neural information processing systems1 citationJan 1, 2025From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space RegularizationGoogle DeepMind · neural information processing systems1 citationJan 1, 2025SSA-COMET: Do LLMs Outperform Learned Metrics in Evaluating MT for Under-Resourced African Languages?Alphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)1 citationJan 1, 2025MetaFaith: Faithful Natural Language Uncertainty Expression in LLMsAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)1 citationJan 1, 2025Evaluating WMT 2025 Metrics Shared Task Submissions on the SSA-MTE African Challenge SetAlphabet · Conference on Machine Translation (WMT)1 citationJan 1, 2025SMOL: Professionally Translated Parallel Data for 115 Under-represented LanguagesAlphabet, Google DeepMind · Conference on Machine Translation (WMT)1 citationJan 1, 2025Feeding Two Birds or Favoring One? Adequacy–Fluency Tradeoffs in Evaluation and Meta-Evaluation of Machine TranslationAlphabet · Conference on Machine Translation (WMT)1 citationJan 1, 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential PrivacyAlphabet · neural information processing systems1 citationJan 1, 2025Sampling 3D Molecular Conformers with Diffusion TransformersGoogle DeepMind · neural information processing systems1 citationJan 1, 2025Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language TranslationAlphabet · neural information processing systems1 citationJan 1, 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning ProblemsGoogle DeepMind · neural information processing systems1 citationJan 1, 2025Safety Pretraining: Toward the Next Generation of Safe AIAlphabet, Google DeepMind · neural information processing systems1 citationJan 1, 2025