Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Confidence Improves Self-Consistency in LLMsAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)112 citationsJan 1, 2025WorldModelBench: Judging Video Generation Models As World ModelsAlphabet, NVIDIA · neural information processing systems111 citationsJan 1, 2025Scaling Computer-Use Grounding via User Interface Decomposition and SynthesisAlibaba · neural information processing systems111 citationsJan 1, 2025Measuring what Matters: Construct Validity in Large Language Model BenchmarksAllen Institute for AI, Google DeepMind · neural information processing systems111 citationsJan 1, 2025LoRA vs Full Fine-tuning: An Illusion of EquivalenceMicrosoft · neural information processing systems111 citationsJan 1, 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level ComputationAlphabet, Google DeepMind · neural information processing systems109 citationsJan 1, 2025The Leaderboard IllusionAllen Institute for AI, Cohere · neural information processing systems109 citationsJan 1, 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM ReasoningMicrosoft · neural information processing systems109 citationsJan 1, 2025TelecomGPT: A Framework to Build Telecom-Specific Large Language ModelsTechnology Innovation Institute · IEEE Transactions on Machine Learning in Communications and Networking109 citationsJan 1, 2025Physics of Language Models: Part 3.2, Knowledge ManipulationMeta · SSRN Electronic Journal109 citationsJan 1, 2025Why Do Multi-Agent LLM Systems Fail?Microsoft · neural information processing systems107 citationsJan 1, 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)Allen Institute for AI · neural information processing systems107 citationsJan 1, 2025Physics of Language Models: Part 1, Learning Hierarchical Language StructuresMeta · SSRN Electronic Journal106 citationsJan 1, 2025Video World Models with Long-term Spatial MemoryGoogle DeepMind · neural information processing systems105 citationsJan 1, 2025Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language ModelsMeta · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)105 citationsJan 1, 2025OmniBench: Towards The Future of Universal Omni-Language ModelsAlibaba, Google DeepMind · neural information processing systems102 citationsJan 1, 2025GUI-Actor: Coordinate-Free Visual Grounding for GUI AgentsMicrosoft · neural information processing systems100 citationsJan 1, 2025EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary AlgorithmsMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)98 citationsJan 1, 2025LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QAZhipu AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)95 citationsJan 1, 2025Anomaly Detection in Network Traffic Using Advanced Machine Learning TechniquesMeta · IEEE Access94 citationsJan 1, 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence FunctionsAnthropic · neural information processing systems93 citationsJan 1, 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement LearningNVIDIA · neural information processing systems92 citationsJan 1, 2025(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary TextsAlibaba · Transactions of the Association for Computational Linguistics90 citationsJan 1, 2025PerceptionLM: Open-Access Data and Models for Detailed Visual UnderstandingAlphabet, Meta · neural information processing systems87 citationsJan 1, 2025Large-Scale Study of Curiosity-Driven LearningOpenAI · Edinburgh Research Explorer (University of Edinburgh)87 citationsJan 1, 2025