Research map / Architectures and efficiency / RNNs and normalization
Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-level aligner (input words plus hidden states) (ablation) | LSTM encoder-aligner-decoder · SAIL single-sentence | accuracy: 68.09 -> 69.98 | Helped |
| add multi-level aligner (input words plus hidden states) (ablation) | LSTM encoder-aligner-decoder · SAIL multi-sentence | accuracy: 24.79 -> 26.07 | Helped |
| add learned alignment instead of uniform averaging (ablation) | LSTM encoder-aligner-decoder · SAIL single-sentence | accuracy: 68.05 -> 69.98 | Helped |
| add learned alignment instead of uniform averaging (ablation) | LSTM encoder-aligner-decoder · SAIL multi-sentence | accuracy: 25.04 -> 26.07 | Helped |
| use bidirectional instead of unidirectional encoder (ablation) | LSTM encoder-aligner-decoder · SAIL single-sentence | accuracy: 67.44 -> 69.98 | Helped |
| add sentence encoder (ablation) | LSTM encoder-aligner-decoder · SAIL single-sentence | accuracy: 61.63 -> 69.98 | Helped |
| add sentence encoder (ablation) | LSTM encoder-aligner-decoder · SAIL multi-sentence | accuracy: 16.67 -> 26.07 | Helped |
| neural seq2seq without linguistic resources vs prior semantic-parsing methods | navigation instruction following · SAIL multi-sentence | accuracy: 30.34 vs 35.44 | Mixed |
Closest papers by meaning
- GOALNET: Interleaving Neural Goal Predicate Inference with Classical Planning for Generalization in Robot Instruction Following (AAAI 2024 · similarity 0.86)
- Improving Instruction-Following in Language Models through Activation Steering (ICLR 2025 · similarity 0.86)
- Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel (ICLR 2025 · similarity 0.85)
- Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks (ICLR 2024 · similarity 0.85)
- Do LLMs ``know'' internally when they follow instructions? (ICLR 2025 · similarity 0.85)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.85)
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.