AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Grounding Spatio-Temporal Language with Transformers

Tristan Karch, Laetitia Teodorescu, Katja Hofmann, Clément Moulin-Frier, Pierre-Yves Oudeyer

NeurIPS 2021 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Aggregate scene and language into a single vector (SFT) instead of per-object Transformer (UT/TFT) (ablation)Transformer · Spatio-temporal sentencesF1: 0.80 -> 0.75Hurt
Use UT/TFT Transformers instead of LSTM baselinesUT/TFT · Held-out sentences, all categoriesF1Improved
Add word-aggregation (WA) to Transformer models (ablation)UT, TFT, SFT · Non-systematic held-out sentencesF1No clear effect
Add word-aggregation to UT models (ablation)UT · Spatio-temporal conceptsF1: 2.38Mixed
Add word-aggregation (split 3, new one-to-one relation) (ablation)UT, SFT, TFT · Split 3 'right of'F1: -0.14, -0.15, -0.20Hurt
Add word-aggregation (split 5, past predicate grasp) (ablation)UT, SFT, TFT · Split 5 'was grasp'F1: 0.71, 0.45, 0.52Improved
Add word-aggregation (split 4, past spatial relation) (ablation)UT, TFT · Split 4 'was left of'F1Hurt
Evaluate on new observations instead of new sentences (known sentences)LSTM baselines · Train sentences, new observationsF1: 0.79 -> 0.82Improved
Evaluate with hard negative examples instead of random negativesTrained models · Systematic generalization splitsF1: less than 5%Hurt
Increase model size with high learning rate in WA variants (ablation)UT-WA, TFT-WA, SFT-WA · Hyperparameter searchstabilityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy