Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Layout-Aware Dreamer for Embodied Visual Referring Expression 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 |
|---|---|---|---|
| add Layout Learner (ablation) | CLIP-feature VLN-DUET baseline · REVERIE Val-unseen | SR: 52.34 -> 56.04 | Helped |
| add Layout Learner (ablation) | CLIP-feature VLN-DUET baseline · REVERIE Val-unseen | RGS: 35.02 -> 37.06 | Helped |
| add Goal Dreamer (ablation) | CLIP-feature VLN-DUET baseline · REVERIE Val-unseen | SR: 52.34 -> 53.45 | Helped |
| add Goal Dreamer (ablation) | CLIP-feature VLN-DUET baseline · REVERIE Val-unseen | RGS: 35.02 -> 34.34 | Hurt |
| add Layout Learner and Goal Dreamer (ablation) | CLIP-feature VLN-DUET baseline · REVERIE Val-unseen | SR: 52.34 -> 57.00 | Helped |
| replace the visual room codebook with a room-type classification head (ablation) | LAD · REVERIE Val-unseen | SR: 57.00 -> 53.73 | Hurt |
| replace the visual room codebook with textual room prompts (ablation) | LAD · REVERIE Val-unseen | SR: 57.00 -> 51.38 | Hurt |
| replace the visual room codebook with textual room prompts (ablation) | LAD · REVERIE Val-unseen | RGS: 37.80 -> 32.38 | Hurt |
| use LAD instead of VLN-DUET | REVERIE · Test-unseen | SR: 52.51 -> 56.53 | Helped |
| use LAD instead of VLN-DUET | REVERIE · Test-unseen | RGS: 31.88 -> 35.31 | Helped |
| use LAD instead of VLN-DUET | SOON · Test Unseen | SR: 33.44 -> 39.59 | Helped |
Closest papers by meaning
- Scene-Intuitive Agent for Remote Embodied Visual Grounding (CVPR 2021 · similarity 0.91)
- Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (NeurIPS 2025 · similarity 0.86)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.86)
- Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents (ICLR 2025 · similarity 0.86)
- Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples (AAAI 2025 · similarity 0.85)
- Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation (NeurIPS 2025 · 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.