Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Improved Balanced Classification with Theoretically Grounded Loss FunctionsAlphabet · neural information processing systemsJan 1, 2025Better Estimation of the Kullback--Leibler Divergence Between Language ModelsGoogle DeepMind · neural information processing systemsJan 1, 2025Proper Hölder-Kullback Dirichlet Diffusion: A Framework for High Dimensional Generative ModelingAlphabet · neural information processing systemsJan 1, 2025Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language ModelsAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025Efficiently Verifiable Proofs of Data AttributionAlphabet · neural information processing systemsJan 1, 2025Efficient Data Selection at Scale via Influence DistillationAlphabet · neural information processing systemsJan 1, 2025REINFORCE Converges to Optimal Policies with Any Learning RateAlphabet, Google DeepMind · neural information processing systemsJan 1, 2025QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?Google DeepMind · neural information processing systemsJan 1, 2025Learning Interactive World Model for Object-Centric Reinforcement LearningGoogle DeepMind · neural information processing systemsJan 1, 2025Adaptive Latent-Space Constraints in Personalized Federated LearningAlphabet · neural information processing systemsJan 1, 2025Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction FollowingGoogle DeepMind · neural information processing systemsJan 1, 2025Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial ObservabilityGoogle DeepMind · neural information processing systemsJan 1, 2025GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New InsightsGoogle DeepMind · neural information processing systemsJan 1, 2025Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant PolicyGoogle DeepMind · neural information processing systemsJan 1, 2025Selective Learning for Deep Time Series ForecastingAlphabet · neural information processing systemsJan 1, 2025Private Set Union with Multiple ContributionsAlphabet · neural information processing systemsJan 1, 2025UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View SynthesisAlphabet · neural information processing systemsJan 1, 2025SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation LearningAlphabet · neural information processing systemsJan 1, 2025ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU DesignAlphabet · neural information processing systemsJan 1, 2025Dimension-adapted Momentum Outscales SGDAlphabet · neural information processing systemsJan 1, 2025On the Edge of Memorization in Diffusion ModelsGoogle DeepMind · neural information processing systemsJan 1, 2025Sequentially Auditing Differential PrivacyAlphabet · neural information processing systemsJan 1, 2025Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement LearningGoogle DeepMind · neural information processing systemsJan 1, 2025GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular UtilityAlphabet · neural information processing systemsJan 1, 2025Curious Causality-Seeking Agents in Open-ended WorldsGoogle DeepMind · neural information processing systemsJan 1, 2025