Research map / Vision-language and multimodal / Robot action and navigation
ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation
Zixuan Chen, Chongkai Gao, Lin Shao, Jieqi Shi, Jing Huo, Yang Gao
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 |
|---|---|---|---|
| use ManiLong-Shot instead of best baseline 3DDA | ManiLong-Shot · RLBench-Oneshot 10 training SH tasks | average success rate (%): 85.0 -> 90.4 | Improved |
| use ManiLong-Shot instead of IMOP on unseen long-horizon tasks | ManiLong-Shot · RLBench-Oneshot 20 unseen LH tasks (one-shot) | average success rate (%): 7.4 -> 30.2 | Improved |
| fine-tune multi-task baselines with 5 demos | RVT2/3DDA/ARP · RLBench-Oneshot 20 unseen LH tasks (one-shot) | average success rate (%): 4.1, 4.5, 4.7 | No clear effect |
| use ManiLong-Shot instead of IMOP in real world | ManiLong-Shot · Real-world LH tasks | average success rate (%): 33.3% -> 60.0% | Improved |
| use rule-based instead of VLM-based (GPT-4o) task decomposition (ablation) | ManiLong-Shot · RLBench-Oneshot 20 unseen LH tasks (one-shot) | success rate | Improved |
| add the positioning network in post-contact region prediction (ablation) | ManiLong-Shot · RLBench-Oneshot 20 unseen LH tasks (one-shot) | success rate | Improved |
| VLM-based decomposition with harder tasks (more primitives) | ManiLong-Shot · RLBench-Oneshot 20 unseen LH tasks (one-shot) | success rate gap vs rule-based | Hurt |
Closest papers by meaning
- OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation (NeurIPS 2025 · similarity 0.90)
- SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation (ICML 2024 · similarity 0.89)
- Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models (ICLR 2024 · similarity 0.88)
- Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control (NeurIPS 2024 · similarity 0.88)
- Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation (CVPR 2025 · similarity 0.88)
- GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation (AAAI 2024 · similarity 0.88)
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.
