Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SERA: Soft-Verified Efficient Repository AgentsAllen Institute for AI · arXiv (Cornell University)Jan 28Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specificationAllen Institute for AI · arXiv (Cornell University)Jan 23Context-Free Recognition with TransformersAllen Institute for AI · arXiv (Cornell University)Jan 5Scale Can’t Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language ReasoningAllen Institute for AI, Mistral AI · Transactions of the Association for Computational Linguistics2 citationsJan 1LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose ModelsAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1The olmOCR Project: Building Fully Open OCR using VLMsAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)1 citationJan 1RotBench: Evaluating Multi-modal Large Language Models on Identifying Image RotationAllen Institute for AI · Conference of the European Chapter of the Association for Computational Linguistics1 citationJan 1AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial MemoriesAllen Institute for AI · Lecture notes in computer science1 citationJan 1Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized RefinementAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)1 citationJan 1Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational ReasoningAllen Institute for AI · Transactions of the Association for Computational Linguistics1 citationJan 1Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model BehaviorAllen Institute for AI · Transactions of the Association for Computational LinguisticsJan 1ScheMatiQ: From Research Question to Structured Data through Interactive Schema DiscoveryAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text GenerationAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and IdeationAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Evaluating Language Model Pluralism through In-the-wild Crowd DiscussionsAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Reading Between the Lines: The One-Sided Conversation ProblemAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Prompts in the Wild: A Large Analyzed Collection of Transactional Prompts in CodeAllen Institute for AI · Linguistic Annotation WorkshopJan 1Language Models Don’t Know What You Want: Evaluating Personalization in Deep Research Needs Real UsersAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Generating Literature-Driven Scientific Theories at ScaleAllen Institute for AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Physics Question Scene Graph: Fine-Grained Evaluation of Physical Plausibility in Text-to-Video GenerationAllen Institute for AI · Lecture notes in computer scienceJan 1Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language ModelsAllen Institute for AI, Microsoft, OpenAI · Lecture notes in computer scienceJan 1Posterior Augmented Flow MatchingAllen Institute for AI, Hugging Face · Lecture notes in computer scienceJan 1MolmoWeb: Open Visual Web Agent and Open Data for the Open WebAllen Institute for AI · Lecture notes in computer scienceJan 1MolmoPoint: Better Pointing for VLMs with Grounding TokensAllen Institute for AI · Lecture notes in computer scienceJan 1A Curious Class of Adpositional Multiword Expressions in KoreanAllen Institute for AI · Workshop on Multiword Expressions (MWE)Jan 1