Showing 1–19 of 19 results
/ Date/ Name
Oct 21, 2024In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory TerminatesJul 16, 2024SPINACH: SPARQL-Based Information Navigation for Challenging Real-World QuestionsDec 15, 2025Explainable reinforcement learning from human feedback to improve alignmentNov 16, 2023SUQL: Conversational Search over Structured and Unstructured Data with Large Language ModelsOct 2, 2025SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement LearningApr 7, 2026DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data StorytellingMay 23, 2023Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over WikidataJun 1, 2024SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic ParsingMay 9, 2025Prompting Large Language Models for Training-Free Non-Intrusive Load MonitoringJun 28, 2023Convergence analysis of a weak Galerkin finite element method on a Shishkin mesh for a singularly perturbed fourth-order problem in 2DJan 31, 2026Steering to Say No: Configurable Refusal via Activation Steering in Vision Language ModelsMar 28, 2026Bayesian factorization via $L_{1/2}$ shrinkageMay 24, 2024Convergence analysis of a weak Galerkin finite element method on a Bakhvalov-type mesh for a singularly perturbed convection-diffusion equation in 2DSep 30, 2025A posteriori error estimation for weak Galerkin method of the fourth-order singularly perturbed problemSep 11, 2024A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and ChallengesNov 11, 2023The stabilizer free weak Galerkin mixed finite elements method for the biharmonic equationSep 25, 2019Strong Aharonov-Bohm quantum interference in simply-connected LaAlO$_3$/SrTiO$_3$ structuresOct 3, 2025The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic FeedbackJul 8, 2024Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets