Research

A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.

Field
Lab

13,724 papers in Computer Science, newest first. Some proceedings carry OpenAlex's date of January 1.

Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web AgentsMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)56 citationsJan 1, 2025MLE-STAR: Machine Learning Engineering Agent via Search and Targeted RefinementAlphabet · neural information processing systems55 citationsJan 1, 2025CoT Red-Handed: Stress Testing Chain-of-Thought MonitoringAlphabet, OpenAI · neural information processing systems55 citationsJan 1, 2025ThinkSLM: Towards Reasoning in Small Language ModelsNVIDIA · Conference on Empirical Methods in Natural Language Processing (EMNLP)55 citationsJan 1, 2025R-KV: Redundancy-aware KV Cache Compression for Reasoning ModelsAlibaba, Microsoft · neural information processing systems55 citationsJan 1, 2025People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated textMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting53 citationsJan 1, 2025Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data GenerationAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. Meeting53 citationsJan 1, 2025Safety Pretraining: Toward the Next Generation of Safe AIAlphabet, Google DeepMind · neural information processing systems52 citationsJan 1, 2025Self-Challenging Language Model AgentsMeta · neural information processing systems52 citationsJan 1, 2025HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden StatesAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting52 citationsJan 1, 2025The Lessons of Developing Process Reward Models in Mathematical ReasoningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)52 citationsJan 1, 2025Less is More: Improving LLM Alignment via Preference Data SelectionAlibaba · neural information processing systems51 citationsJan 1, 2025OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative GeneralizationAllen Institute for AI · neural information processing systems50 citationsJan 1, 2025PolyMath: Evaluating Mathematical Reasoning in Multilingual ContextsAlibaba · neural information processing systems50 citationsJan 1, 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified DatasetMicrosoft · neural information processing systems50 citationsJan 1, 2025Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting50 citationsJan 1, 2025Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee DiscussionsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting50 citationsJan 1, 2025Towards Understanding Camera Motions in Any VideoGoogle DeepMind · neural information processing systems49 citationsJan 1, 2025mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic DataMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)49 citationsJan 1, 2025Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree SearchSakana AI · neural information processing systems48 citationsJan 1, 2025PAPILLON: Privacy Preservation from Internet-based and Local Language Model EnsemblesDatabricks · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)48 citationsJan 1, 2025Rethinking Data Selection at Scale: Random Selection is Almost All You NeedAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)47 citationsJan 1, 2025Do Language Models Use Their Depth Efficiently?OpenAI · neural information processing systems47 citationsJan 1, 2025VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-ThoughtAlibaba · neural information processing systems47 citationsJan 1, 2025Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular VideosNVIDIA · neural information processing systems47 citationsJan 1, 2025