Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision ProcessesAllen Institute for AI · arXiv (Cornell University)Jul 14A Shared Subcircuit Lets LLMs Count Down Across TasksAnthropic · arXiv (Cornell University)Jul 14ReflectVLN: Training Vision-Language Navigation Agents with Reflective ReasoningAlibaba · arXiv (Cornell University)Jul 14Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation ModelsNVIDIA · arXiv (Cornell University)Jul 14Rethinking the Evaluation of Harness Evolution for AgentsAllen Institute for AI · arXiv (Cornell University)Jul 14Exposure-Based Reinforcement Learning to RankAlphabet · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)Jul 14Efficient Adaptation of Chemical Language Models for Molecular Property PredictionTechnology Innovation Institute · Translational InsightsJul 14Prior-Data Fitted Networks as Tabular Foundation Models for Ranking in Low-Data SettingsCohere · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)Jul 14What Makes AI Slop (or Not)Alphabet · ACM SIGGRAPH Conference (SIGGRAPH)Jul 14LLM-Driven Usefulness Judgment for Web Search EvaluationMeta · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)Jul 14The limits of sequence-based biosecurity screening tools in the age of AI-assisted protein designMicrosoft · Frontiers in Bioengineering and Biotechnology5 citationsJul 13Self-Improving Robot Policy with Compositional World ModelHorizon Robotics · Robotics: Science and Systems2 citationsJul 13OpenFrontier: General Navigation with Visual-Language Grounded FrontiersMicrosoft · Robotics: Science and SystemsJul 13Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop FrameworkMicrosoft · arXiv (Cornell University)Jul 13Omni-Decision: Evidence-Ledger Planning for Omni-Modal AgentsAlibaba · arXiv (Cornell University)Jul 13Beyond the Single Camera: Agentic Multi-View Reasoning in Sports Video UnderstandingMicrosoft · arXiv (Cornell University)Jul 13Domain-Aware Scaling Laws Uncover Data SynergyMicrosoft · arXiv (Cornell University)Jul 13MemExchange: Utility-Driven Distributed Memory Reallocation for Multi-Tenant DatacentersMicrosoft · arXiv (Cornell University)Jul 13Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge BiasAlibaba · arXiv (Cornell University)Jul 13Perspective on Self-Supervised Transformers for Scalable Data Analysis, Retrievals, and Discovery in GeosciencesAllen Institute for AI · Artificial Intelligence for the Earth SystemsJul 13Influence of camera geometry on 3D joint angle estimation in markerless motion captureAlphabet · Frontiers in Sports and Active LivingJul 13Strategies for restructuring information architectureMicrosoft · Arcos DesignJul 13Masked attribution-based probing of strategies as a computational framework to align human, non-human primate, and model explanationsAnthropic · Communications PsychologyJul 13AI for Systems is "AGI-Complete"Alphabet · ACM SIGOPS Operating Systems ReviewJul 13Latent Policy Steering through One-Step Flow PoliciesMicrosoft · Robotics: Science and SystemsJul 13