Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented GenerationLG AI Research · Findings of the Association for Computational Linguistics: NAACL4 citationsJan 1, 2025LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment StrategyAlibaba · Findings of the Association for Computational Linguistics: NAACL4 citationsJan 1, 2025PolySAT: Word-level Bit-vector Reasoning in Z3Microsoft · Lecture notes in computer science4 citationsJan 1, 2025DynHAC : Fully Dynamic Approximate Hierarchical Agglomerative ClusteringAlphabet · Society for Industrial and Applied Mathematics eBooks4 citationsJan 1, 2025Pluralistic Salient Object DetectionMicrosoft · IEEE Transactions on Image Processing4 citationsJan 1, 2025Societal impacts and opportunities of federated learningMicrosoft · Chinese Journal of Sociology4 citationsJan 1, 2025Analyzing Similarity Metrics for Data Selection for Language Model PretrainingAlphabet, Google DeepMind · neural information processing systems4 citationsJan 1, 2025Improved Spectral Density Estimation via Explicit and Implicit DeflationAlphabet · Society for Industrial and Applied Mathematics eBooks4 citationsJan 1, 2025Aim My Robot: Precision Local Navigation to Any ObjectNVIDIA · AUVSI XPONENTIAL4 citationsJan 1, 2025Efficient Adaptive Federated OptimizationAlphabet · neural information processing systems4 citationsJan 1, 20253D-Prover: Diversity Driven Theorem Proving With Determinantal Point ProcessesGoogle DeepMind · neural information processing systems4 citationsJan 1, 2025A Closer Look at Graph Transformers: Cross-Aggregation and BeyondAlibaba · neural information processing systems3 citationsJan 1, 2025Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled LearningAlibaba · neural information processing systems3 citationsJan 1, 2025SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAIOpenAI · neural information processing systems3 citationsJan 1, 2025SeerAttention: Self-distilled Attention Gating for Efficient Long-context PrefillingMicrosoft, NVIDIA · neural information processing systems3 citationsJan 1, 2025Subsampled Ensemble Can Improve Generalization Tail ExponentiallyAlibaba · neural information processing systems3 citationsJan 1, 2025Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement LearningGoogle DeepMind · neural information processing systems3 citationsJan 1, 2025VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language ModelsAlibaba · neural information processing systems3 citationsJan 1, 2025AdaptGrad: Adaptive Sampling to Reduce NoiseMicrosoft · neural information processing systems3 citationsJan 1, 2025Interpretable Next-token Prediction via the Generalized Induction HeadMicrosoft · neural information processing systems3 citationsJan 1, 2025Exploring the limits of strong membership inference attacks on large language modelsAnthropic, Google DeepMind, OpenAI · neural information processing systems3 citationsJan 1, 2025Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is AttainableAlphabet · neural information processing systems3 citationsJan 1, 2025Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM DecodingAlibaba · neural information processing systems3 citationsJan 1, 2025AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic ScenariosZhipu AI · neural information processing systems3 citationsJan 1, 2025Generative Model Inversion Through the Lens of the Manifold HypothesisMicrosoft · neural information processing systems3 citationsJan 1, 2025