Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language ModelAlphabet · neural information processing systems3 citationsJan 1, 2025Findings of the WMT25 General Machine Translation Shared Task: Time to Stop Evaluating on Easy Test SetsAlphabet, Microsoft · Conference on Machine Translation (WMT)3 citationsJan 1, 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task AutomationGoogle DeepMind · neural information processing systems3 citationsJan 1, 2025Towards Understanding Camera Motions in Any VideoGoogle DeepMind · neural information processing systems3 citationsJan 1, 2025Quantum One-Time Protection of Any Randomized AlgorithmAlphabet · Lecture notes in computer science3 citationsJan 1, 2025Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent InteractionsAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)3 citationsJan 1, 2025CausalGraph2LLM: Evaluating LLMs for Causal QueriesAlphabet · Findings of the Association for Computational Linguistics: NAACL3 citationsJan 1, 2025Knowledge Graph Reasoning With Self-Supervised Reinforcement LearningAlphabet · IEEE Transactions on Audio Speech and Language Processing3 citationsJan 1, 2025Almost Tight Bounds for Differentially Private Densest SubgraphAlphabet · Society for Industrial and Applied Mathematics eBooks3 citationsJan 1, 2025Congestion-Approximators from the Bottom UpAlphabet · Society for Industrial and Applied Mathematics eBooks3 citationsJan 1, 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level ComputationAlphabet, Google DeepMind · neural information processing systems2 citationsJan 1, 2025Generating Creative Chess PuzzlesAlphabet, Google DeepMind · neural information processing systems2 citationsJan 1, 2025Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation DataAlphabet · neural information processing systems2 citationsJan 1, 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-SearchGoogle DeepMind, NVIDIA · neural information processing systems2 citationsJan 1, 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and GenerationAlphabet · neural information processing systems2 citationsJan 1, 2025Learning 3D Persistent Embodied World ModelsGoogle DeepMind · neural information processing systems2 citationsJan 1, 2025WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenariosAlphabet, Meta, Microsoft · neural information processing systems2 citationsJan 1, 2025OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language PromptsGoogle DeepMind · neural information processing systems2 citationsJan 1, 2025Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential PrivacyGoogle DeepMind · neural information processing systems2 citationsJan 1, 2025LayerIF: Estimating Layer Quality for Large Language Models using Influence FunctionsAlphabet · neural information processing systems2 citationsJan 1, 2025Improving Informally Romanized Language IdentificationAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1, 2025EquiBench: Benchmarking Large Language Models’ Reasoning about Program Semantics via Equivalence CheckingAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1, 2025ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of MomentsAlphabet · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1, 2025LegoSLM: Connecting LLM with Speech Encoder using CTC PosteriorsAlphabet, Google DeepMind · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1, 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity RewardAlphabet, Google DeepMind · neural information processing systems2 citationsJan 1, 2025