Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text GenerationAllen Institute for AI · arXiv (Cornell University)Jun 6Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text GenerationAllen Institute for AI · arXiv (Cornell University)Jun 6TAM: Torque Adaptation Module for Robust Motion Transfer in ManipulationAllen Institute for AI · arXiv (Cornell University)Jun 4The One Ring: a Robotic Indoor Navigation GeneralistAllen Institute for AI · Proceedings - IEEE International Conference on Robotics and Automation/ProceedingsJun 1Scideator: Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty EvaluationAllen Institute for AI · ACM Conference on AI and Agentic Systems (CAIS)May 22A Language for Describing Agentic LLM ContextsAllen Institute for AI · ACM Conference on AI and Agentic Systems (CAIS)May 22Reinforcement Learning over Predictive Distributions for LLM RegressionAllen Institute for AI · arXiv (Cornell University)May 20Echoes of Citations: Automated Extraction of Claims from Full Scientific PapersAllen Institute for AI, Google DeepMind, Microsoft · Proceedings of the AAAI Symposium SeriesMay 18ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art DiscoveryAllen Institute for AI · arXiv (Cornell University)May 16A Theory of Training Profit-Optimal LLMsAllen Institute for AI · arXiv (Cornell University)May 14How Much is Brain Data Worth for Machine Learning?Allen Institute for AI · arXiv (Cornell University)May 10Toward Better Geometric Representations for Molecule Generative ModelsAllen Institute for AI · arXiv (Cornell University)May 8EMO: Pretraining Mixture of Experts for Emergent ModularityAllen Institute for AI · arXiv (Cornell University)May 7EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative RubricsAllen Institute for AI · arXiv (Cornell University)May 5Training Transformers as a Universal ComputerAllen Institute for AI · arXiv (Cornell University)Apr 28SFT-then-RL Outperforms Mixed-Policy Methods for LLM ReasoningAllen Institute for AI · arXiv (Cornell University)Apr 26DRACULA: Hunting for the Actions Users Want Deep Research Agents to ExecuteAllen Institute for AI · arXiv (Cornell University)Apr 26Accuracy Certificates for Convex Optimization at Accelerated Rates via Primal-Dual AveragingAllen Institute for AI · arXiv (Cornell University)Apr 20Train Separately, Merge Together: Modular Post-Training with Mixture-of-ExpertsAllen Institute for AI · arXiv (Cornell University)Apr 20Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter CalibrationAllen Institute for AI · arXiv (Cornell University)Apr 14Cocoa: Co-Planning and Co-Execution with AI AgentsAllen Institute for AI · CHI Conference on Human Factors in Computing Systems7 citationsApr 13Science and Technology for Augmenting Reading (STAR)Allen Institute for AI · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)1 citationApr 13ScheMatiQ: From Research Question to Structured Data through Interactive Schema DiscoveryAllen Institute for AI · arXiv (Cornell University)Apr 10ScheMatiQ: From Research Question to Structured Data through Interactive Schema DiscoveryAllen Institute for AI · arXiv (Cornell University)Apr 10Olmo Hybrid: From Theory to Practice and BackAllen Institute for AI · arXiv (Cornell University)Apr 3