paper-with-me

홈 › Papers

FILM: Following Instructions in Language with Modular Methods

2021-10-12 · ICLR 2022 4 · So Yeon Min, Devendra Singh Chaplot, Pradeep Ravikumar, Yonatan Bisk, Ruslan Salakhutdinov

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.

📄 PDF Abstract BibTeX arXiv:2110.07342

Code (1)

soyeonm/film 공식 구현 pytorch

Tasks

Imitation LearningInstruction Following

Similar Papers 제목 키워드 기반

Modular Networks for Compositional Instruction Following

2020-10-24 · NAACL 2021 4 · Rodolfo Corona, Daniel Fried, Coline Devin, Dan Klein 외

Standard architectures used in instruction following often struggle on novel compositions of subgoals (e.g. navigating to landmarks or picking up objects) observed during training. We propose a modular architecture for f…

Instruction Following

Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following

2022-11-07 · Yuki Inoue, Hiroki Ohashi

Embodied Instruction Following (EIF) studies how autonomous mobile manipulation robots should be controlled to accomplish long-horizon tasks described by natural language instructions. While much research on EIF is condu…

Instruction FollowingLanguage ModelingLanguage ModellingLarge Language Model

DANLI: Deliberative Agent for Following Natural Language Instructions

2022-10-22 · Yichi Zhang, Jianing Yang, Jiayi Pan, Shane Storks 외

Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and im…

Instruction FollowingVision-Language Navigation

Improving Instruction-Following in Language Models through Activation Steering

2024-10-15 · Alessandro Stolfo, Vidhisha Balachandran, Safoora Yousefi, Eric Horvitz 외

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations f…

Instruction FollowingText Generation

Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities

2026-01-26 · Alberto Purpura, Li Wang, Sahil Badyal, Eugenio Beaufrand 외 arxiv

Reliably ensuring Large Language Models (LLMs) follow complex instructions is a critical challenge, as existing benchmarks often fail to reflect real-world use or isolate compliance from task success. We introduce MOSAIC…