Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning EngineeringAlphabet, Google DeepMind · neural information processing systems38 citationsJan 1, 2025Efficient Part-level 3D Object Generation via Dual Volume PackingNVIDIA · neural information processing systems38 citationsJan 1, 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM ReasoningMicrosoft · neural information processing systems38 citationsJan 1, 2025Scaling Laws For Scalable OversightAnthropic, Google DeepMind · neural information processing systems38 citationsJan 1, 2025Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered AgentsMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)38 citationsJan 1, 2025MindJourney: Test-Time Scaling with World Models for Spatial ReasoningGoogle DeepMind, Microsoft · neural information processing systems38 citationsJan 1, 2025Reverse Thinking Makes LLMs Stronger ReasonersAlphabet, Google DeepMind · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)38 citationsJan 1, 2025Informed Correctors for Discrete Diffusion ModelsGoogle DeepMind, Microsoft · neural information processing systems38 citationsJan 1, 2025A Unified Metric Architecture for AI Infrastructure: A Cross-Layer Taxonomy Integrating Economics, Performance, and EfficiencyAlphabet · SSRN Electronic Journal37 citationsJan 1, 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering TasksAlibaba · neural information processing systems37 citationsJan 1, 2025Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model PerformanceAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)37 citationsJan 1, 2025AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented GenerationAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)37 citationsJan 1, 2025SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multirobot NavigationMicrosoft · IEEE Transactions on Robotics37 citationsJan 1, 2025Bitnet.cpp: Efficient Edge Inference for Ternary LLMsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting37 citationsJan 1, 2025AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter MergingAlibaba · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)37 citationsJan 1, 2025Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory ConstraintsAlibaba · SSRN Electronic Journal37 citationsJan 1, 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance GenerationMicrosoft · neural information processing systems36 citationsJan 1, 2025MiniMax-Remover: Taming Bad Noise Helps Video Object RemovalGoogle DeepMind · neural information processing systems36 citationsJan 1, 2025Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement FinetuningMicrosoft · neural information processing systems36 citationsJan 1, 2025The Distracting Effect: Understanding Irrelevant Passages in RAGTechnology Innovation Institute · Proceedings of the conference - Association for Computational Linguistics. Meeting36 citationsJan 1, 2025ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMsNVIDIA · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)36 citationsJan 1, 2025Rope to Nope and Back Again: A New Hybrid Attention StrategyCohere · neural information processing systems36 citationsJan 1, 2025CLEVER: A Curated Benchmark for Formally Verified Code GenerationGoogle DeepMind · neural information processing systems35 citationsJan 1, 2025The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed TextAllen Institute for AI, Google DeepMind, Hugging Face · neural information processing systems35 citationsJan 1, 2025M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning FrameworkAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)35 citationsJan 1, 2025