Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Sampling from Your Language Model One Byte at a TimeAllen Institute for AI · arXiv (Cornell University)Jun 17, 2025Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language ModelsAllen Institute for AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings66 citationsJun 10, 2025One Diffusion to Generate Them AllAllen Institute for AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings9 citationsJun 10, 2025ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data StreamsAllen Institute for AI, LG AI Research · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings3 citationsJun 10, 2025Synthetic Visual GenomeAllen Institute for AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings3 citationsJun 10, 2025Semantic and Expressive Variation in Image Captions Across LanguagesAllen Institute for AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings1 citationJun 10, 2025RewardBench 2: Advancing Reward Model EvaluationAllen Institute for AI · arXiv (Cornell University)1 citationJun 2, 2025Breaking mBad! Supervised Fine-tuning for Cross-Lingual DetoxificationAllen Institute for AI · arXiv (Cornell University)May 22, 2025FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-TuningAllen Institute for AI · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings10 citationsMay 19, 2025A Reality Check of Language Models as Formalizers on Constraint Satisfaction ProblemsAllen Institute for AI · arXiv (Cornell University)May 19, 2025PointArena: Probing Multimodal Grounding Through Language-Guided PointingAllen Institute for AI · arXiv (Cornell University)May 15, 2025Derivational morphology reveals analogical generalization in large language modelsAllen Institute for AI · Proceedings of the National Academy of Sciences7 citationsMay 9, 2025ReasonIR: Training Retrievers for Reasoning TasksAllen Institute for AI · arXiv (Cornell University)2 citationsApr 29, 2025Social-RAG: Retrieving from Group Interactions to Socially Ground AI GenerationAllen Institute for AI · CHI Conference on Human Factors in Computing Systems8 citationsApr 24, 2025Ai2 Scholar QA: Organized Literature Synthesis with AttributionAllen Institute for AI · arXiv (Cornell University)Apr 15, 2025Reasoning Models Can Be Effective Without ThinkingAllen Institute for AI · arXiv (Cornell University)Apr 14, 2025Calibrating Large Language Models with Sample ConsistencyAllen Institute for AI, Microsoft · Proceedings of the AAAI Conference on Artificial Intelligence21 citationsApr 11, 2025RouterRetriever: Routing over a Mixture of Expert Embedding ModelsAllen Institute for AI · Proceedings of the AAAI Conference on Artificial Intelligence4 citationsApr 11, 2025A Survey on Personalized and Pluralistic Preference Alignment in Large Language ModelsAllen Institute for AI · arXiv (Cornell University)Apr 9, 2025OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training TokensAllen Institute for AI · arXiv (Cornell University)Apr 9, 2025Foundation Model and Temporal Priors-guided Transductive Few-shot Action RecognitionAllen Institute for AI · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025The global landscape of academic guidelines for generative AI and LLMsAllen Institute for AI · Nature Human Behaviour10 citationsMar 3, 2025Designing LLM Chains by Adapting Techniques from Crowdsourcing WorkflowsAllen Institute for AI · ACM Transactions on Computer-Human Interaction18 citationsFeb 7, 2025ZebraLogic: On the Scaling Limits of LLMs for Logical ReasoningAllen Institute for AI · arXiv (Cornell University)1 citationFeb 3, 2025s1: Simple test-time scalingAllen Institute for AI · arXiv (Cornell University)12 citationsJan 31, 2025