Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Out of Style: RAG’s Fragility to Linguistic VariationAllen Institute for AI · Conference of the European Chapter of the Association for Computational LinguisticsJan 1Incentivizing Strong Reasoning from Weak SupervisionAlibaba, Allen Institute for AI · Conference of the European Chapter of the Association for Computational LinguisticsJan 1V-Co: A Closer Look at Visual Representation Alignment via Co-DenoisingAllen Institute for AI, Meta · Lecture notes in computer scienceJan 1M o N a C o : More Natural and Complex Questions for Reasoning Across Dozens of DocumentsAllen Institute for AI · Transactions of the Association for Computational LinguisticsJan 1CodeDistiller: Automatically Generating Code Libraries for Scientific Coding AgentsAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Reasoning Up the Instruction Ladder for Controllable Language ModelsAllen Institute for AI, Microsoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Distilling to Hybrid Attention Models via KL-Guided Layer SelectionAllen Institute for AI · arXiv (Cornell University)Dec 23, 2025Olmo 3Allen Institute for AI · arXiv (Cornell University)5 citationsDec 15, 2025Keeping Humans in the Loop: The Role of Human Skills in Large Language Model–Based Natural Language ApplicationsAllen Institute for AI · Annual Review of Linguistics1 citationDec 8, 2025The Reality Gap in Robotics: Challenges, Solutions, and Best PracticesAllen Institute for AI, NVIDIA · Annual Review of Control Robotics and Autonomous Systems9 citationsDec 2, 2025RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable EnvironmentsAllen Institute for AI · arXiv (Cornell University)Nov 10, 2025The 1st Workshop on LLM Agents for Social SimulationAllen Institute for AI · ACM International Conference on Information and Knowledge Management (CIKM)1 citationNov 8, 2025DiScoFormer: Plug-In Density and Score Estimation with TransformersAllen Institute for AI · arXiv (Cornell University)Nov 8, 2025Reading Between the Lines: The One-Sided Conversation ProblemAllen Institute for AI · arXiv (Cornell University)Nov 4, 2025Reading Between the Lines: The One-Sided Conversation ProblemAllen Institute for AI · arXiv (Cornell University)Nov 4, 2025Leveraging Hierarchical Organization for Medical Multi-document SummarizationAllen Institute for AI · arXiv (Cornell University)Oct 27, 2025MultiRef: Controllable Image Generation with Multiple Visual ReferencesAllen Institute for AI · ACM International Conference on Multimedia (ACM MM)Oct 25, 2025olmOCR 2: Unit Test Rewards for Document OCRAllen Institute for AI · arXiv (Cornell University)1 citationOct 22, 2025PaperPing: A Socially-aware AI Agent that Recommends Academic Papers to Research Group Chats with Contextualized ExplanationsAllen Institute for AI · ACM Conference on Computer Supported Cooperative Work (CSCW)1 citationOct 17, 2025ScholarEval: Research Idea Evaluation Grounded in LiteratureAllen Institute for AI · arXiv (Cornell University)Oct 17, 2025Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling PerspectiveAllen Institute for AI · arXiv (Cornell University)Oct 16, 2025HARPA: A Testability-Driven, Literature-Grounded Framework for Research IdeationAllen Institute for AI · arXiv (Cornell University)Oct 1, 2025A Large-Scale Study of Reranker Relevance Feedback at InferenceAllen Institute for AI · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)1 citationJul 13, 2025On the Predictive Power of Representation Dispersion in Language ModelsAllen Institute for AI · arXiv (Cornell University)Jun 30, 2025LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMRAllen Institute for AI · arXiv (Cornell University)Jun 23, 2025