Research map / Vision-language and multimodal / Robot action and navigation
Gated-Attention Architectures for Task-Oriented Language Grounding
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 |
|---|---|---|---|
| Replace concatenation with Gated-Attention | A3C · Easy MT | accuracy: 1.00 -> 1.00 | No clear effect |
| Replace concatenation with Gated-Attention | A3C · Easy ZSL | accuracy: 0.80 -> 0.81 | Helped |
| Replace concatenation with Gated-Attention | A3C · Medium MT | accuracy: 0.80 -> 0.89 | Helped |
| Replace concatenation with Gated-Attention | A3C · Medium ZSL | accuracy: 0.54 -> 0.75 | Helped |
| Replace concatenation with Gated-Attention | A3C · Hard MT | accuracy: 0.24 -> 0.83 | Helped |
| Replace concatenation with Gated-Attention | A3C · Hard ZSL | accuracy: 0.12 -> 0.73 | Helped |
| Replace concatenation with Gated-Attention | Behavioral Cloning · Easy MT | accuracy: 0.86 -> 0.97 | Helped |
| Replace concatenation with Gated-Attention | Behavioral Cloning · Easy ZSL | accuracy: 0.71 -> 0.81 | Helped |
| Replace concatenation with Gated-Attention | DAgger · Medium MT | accuracy: 0.45 -> 0.55 | Helped |
| Replace concatenation with Gated-Attention | DAgger · Medium ZSL | accuracy: 0.23 -> 0.40 | Helped |
| Replace concatenation with Gated-Attention | Behavioral Cloning · Hard MT | accuracy: 0.20 -> 0.36 | Helped |
| Replace concatenation with Gated-Attention | DAgger · Hard ZSL | accuracy: 0.13 -> 0.30 | Helped |
Closest papers by meaning
- Bridging Environments and Language with Rendering Functions and Vision-Language Models (ICML 2024 · similarity 0.88)
- A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning (CVPR 2023 · similarity 0.88)
- Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data (NeurIPS 2025 · similarity 0.87)
- DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding (ICLR 2025 · similarity 0.86)
- Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks (ICLR 2024 · similarity 0.85)
- D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation (CVPR 2026 · 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.