Research map / Multi-agent systems and games / Human-AI and goal-conditioned
HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments
Ruijie Tang, Chenye Zou, Guoquan Wu, Jun Wei, Wei Chen, Jiaxin Zhu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add hierarchical carrier-carried structure (ablation) | HitMem · Dyna-THOR | SR: 46.67 -> 51.67 | Improved |
| add temporal decay mechanism (ablation) | HitMem · Dyna-THOR | SPL: 20.45 -> 34.24 | Improved |
| add context-aware retrieval strategy (with decay) (ablation) | HitMem · Dyna-THOR | SR: 31.67 -> 51.67 | Improved |
| add class affinity stage to trajectory-based filtering (ablation) | HitMem · Dyna-THOR | SR: 40.00 -> 51.67 | Improved |
| add trajectory filtering stage to affinity scanning (ablation) | HitMem · Dyna-THOR | SR: 46.67 -> 51.67 | Improved |
| drop 30% of trajectory points (ablation) | HitMem · Dyna-THOR | SR: 51.67 -> 50.00 | No clear effect |
| add Gaussian noise to trajectory (ablation) | HitMem · Dyna-THOR | SR: 51.67 -> 50.00 | No clear effect |
| use vague instead of clear task descriptions (ablation) | HitMem with GPT-4o · Dyna-THOR | SR: 51.67 -> 28.33 | Hurt |
| use Gemini-2.5-pro instead of GPT-4o for planning (ablation) | HitMem · Dyna-THOR (clear instructions) | SR: 51.67 -> 48.33 | Hurt |
| apply HitMem zero-shot to ALFRED with relocation disturbance | HitMem vs DynaMem · ALFRED valid_unseen | SR: 41.18 -> 52.94 | Improved |
| choose decay rate lambda by scene scale (ablation) | HitMem · RoboTHOR multi-room | SR | Mixed |
Closest papers by meaning
- 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning (CVPR 2025 · similarity 0.91)
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.88)
- Video World Models with Long-term Spatial Memory (NeurIPS 2025 · similarity 0.87)
- ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.87)
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation (NeurIPS 2025 · similarity 0.87)
- 3D-SPATIAL MULTIMODAL MEMORY (ICLR 2025 · similarity 0.86)
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.
