Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Generalizable Reasoning through Compositional Energy MinimizationGoogle DeepMind · neural information processing systemsJan 1, 2025Training Language Models to Generate Quality Code with Program Analysis FeedbackAnthropic, Google DeepMind, Microsoft · neural information processing systemsJan 1, 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward ModelsAlphabet, Microsoft · neural information processing systemsJan 1, 2025Model Merging in Pre-training of Large Language ModelsAlphabet · neural information processing systemsJan 1, 2025Tight Bounds for Answering Adaptively Chosen Concentrated QueriesAlphabet · neural information processing systemsJan 1, 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLAlphabet, Google DeepMind, Meta · neural information processing systemsJan 1, 2025Imagined AutocurriculaGoogle DeepMind · neural information processing systemsJan 1, 2025CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow MatchingAlphabet · neural information processing systemsJan 1, 2025Robust and Diverse Multi-Agent Learning via Rational Policy GradientGoogle DeepMind · neural information processing systemsJan 1, 2025Reconstruction and Secrecy under Approximate Distance QueriesAlphabet · neural information processing systemsJan 1, 2025MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data CurationAlphabet · neural information processing systemsJan 1, 2025Quantifying Cross-Modality Memorization in Vision-Language ModelsAlphabet · neural information processing systemsJan 1, 2025Infinitely Divisible Noise for Differential Privacy: Nearly Optimal Error in the High $\varepsilon$ RegimeAlphabet · arXiv (Cornell University)Jan 1, 2025Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image RestorationAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025A Clean Slate for Offline Reinforcement LearningGoogle DeepMind · neural information processing systemsJan 1, 2025Machine Unlearning under OverparameterizationAlphabet · neural information processing systemsJan 1, 2025RLHF Algorithms Ranked: An Extensive Evaluation Across Diverse Tasks, Rewards, and HyperparametersAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025BullyBench: Youth & Experts-in-the-loop Framework for Intrinsic and Extrinsic Cyberbullying NLP BenchmarkingAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025On Relation-Specific Neurons in Large Language ModelsGoogle DeepMind · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Reliable and Cost-Effective Exploratory Data Analysis via Graph-Guided RAGAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language ModelsAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?Google DeepMind · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025When Allies Turn Foes: Exploring Group Characteristics of LLM-Based Multi-Agent Collaborative Systems Under Adversarial AttacksAlphabet · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption ModelsGoogle DeepMind · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025Internal states before wait modulate reasoning patternsAlphabet, Google DeepMind · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025