Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions
The recently proposed ALFRED challenge task aims for a virtual robotic agent to complete complex multi-step everyday tasks in a virtual home environment from high-level natural language directives, such as "put a hot piece of bread on a plate". Currently, the best-performing models are able to complete less than 5% of these tasks successfully. In this work we focus on modeling the translation problem of converting natural language directives into detailed multi-step sequences of actions that accomplish those goals in the virtual environment. We empirically demonstrate that it is possible to generate gold multi-step plans from language directives alone without any visual input in 26% of unseen cases. When a small amount of visual information is incorporated, namely the starting location in the virtual environment, our best-performing GPT-2 model successfully generates gold command sequences in 58% of cases. Our results suggest that contextualized language models may provide strong visual semantic planning modules for grounded virtual agents.
Code (1)
Tasks
TranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion
Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos. We introduce pause-and-think-T, a reasoning-centric training dataset that encourages mode…
Scene UnderstandingAnswer GenerationVisually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions
The recently proposed ALFRED challenge task aims for a virtual robotic agent to complete complex multi-step everyday tasks in a virtual home environment from high-level natural language directives, such as {``}put a hot …
TranslationAsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback
With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than na…
Visual GroundingReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually ground…
Continual PretrainingAttending Self-Attention: A Case Study of Visually Grounded Supervision in Vision-and-Language Transformers
The impressive performances of pre-trained visually grounded language models have motivated a growing body of research investigating what has been learned during the pre-training. As a lot of these models are based on Tr…
Language ModelingLanguage ModellingVisual Grounding