Recent methods for embodied instruction following are typically trained end-to-end using imitation learning. This often requires the use of expert trajectories and low-level language instructions. Such approaches assume that neural states will integrate multimodal semantics to perform state tracking, building spatial memory, exploration, and long-term planning. In contrast, we propose a modular method with structured representations that (1) builds a semantic map of the scene and (2) performs exploration with a semantic search policy, to achieve the natural language goal. Our modular method achieves SOTA performance (24.46 %) with a substantial (8.17 % absolute) gap from previous work while using less data by eschewing both expert trajectories and low-level instructions. Leveraging low-level language, however, can further increase our performance (26.49 %). Our findings suggest that an explicit spatial memory and a semantic search policy can provide a stronger and more general representation for state-tracking and guidance, even in the absence of expert trajectories or low-level instructions.
FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema
University of Warwick(华威大学);Tecent YouTu Lab(腾讯优酷实验室);East China Normal University(华东师范大学);King’s College London(伦敦国王学院);The Alan Turing Institute(艾伦·图灵研究所)
A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment
Microsoft Healthcare & Life Sciences(微软医疗与生命科学);Microsoft Research Montréal(微软研究院蒙特利尔);Mila, Université de Montréal(蒙特利尔大学米拉研究所);IKIM, University Hospital Essen(埃森大学医院人工智能医学研究所);Cancer Research Center Cologne Essen(科隆埃森癌症研究中心);German Cancer Consortium(德国癌症联盟);TU Dortmund(多特蒙德工业大学)
AI-Driven Modular Services for Accessible Multilingual Education in Immersive Extended Reality Settings: Integrating Speech Processing, Translation, and Sign Language Rendering
Institute of Communications and Computer Systems (ICCS)(通信与计算机系统研究所);DASKALOS-APPS;National Technical University of Athens(雅典国家技术大学);University of Exeter(埃克塞特大学)
AIAP: A No-Code Workflow Builder for Non-Experts with Natural Language and Multi-Agent Collaboration
Department of Animation, \ University of Art \& Design Uiwang-si Gyeonggi-do Republic of Korea;Graduate School of Information, \ University Seoul Republic of Korea;Department of Animation, \ University of Art \& Design;Graduate School of Information, \ University