Research map / Vision-language and multimodal / Robot action and navigation
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
Xiyin Zeng, Yuyu Sun, Haoyang Li, Shouqiang Liu, Hao Wang
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 HPCC multi-level predictive correction (ablation) | ReCAPA · Behavior (EmbodiedAgentInterface) | success rate: 59.3 -> 72.2 | Improved |
| add trajectory level to action+subgoal HPCC (ablation) | ReCAPA HPCC · AI2-THOR | success rate: 0.65 -> 0.75 | Improved |
| add subgoal level (ablation) | ReCAPA · Behavior (EmbodiedAgentInterface) | success rate: 62.8 -> 72.2 | Improved |
| use hierarchy instead of FlatHead single decoder (ablation) | ReCAPA · Behavior (EmbodiedAgentInterface) | success rate: 49.3 -> 72.2 | Improved |
| add Sinkhorn and Score-field alignment (ablation) | ReCAPA · Behavior (EmbodiedAgentInterface) | success rate: 65.8 -> 72.2 | Improved |
| use Sinkhorn alone instead of Score-field alone (ablation) | ReCAPA alignment · Behavior (EmbodiedAgentInterface) | success rate: 64.4 -> 66.1 | Improved |
| replace Sinkhorn with KL divergence (ablation) | ReCAPA alignment · VisualAgentBench Minecraft | success rate: 66.7 -> 67.0 | Mixed |
| replace HPCC with PPO flat RL (ablation) | ReCAPA · AI2-THOR | success rate: 0.75 -> 0.59 | Hurt |
| replace HPCC with HIRO fixed-interval subgoals (ablation) | ReCAPA · VirtualHome | success rate: 70.5 -> 62.7 | Hurt |
| joint training of all levels instead of separate bottom-up training (ablation) | ReCAPA · AI2-THOR | success rate: 0.59 -> 0.75 | Improved |
| train trajectory level jointly instead of freezing it (ablation) | ReCAPA · Behavior (EmbodiedAgentInterface) | success rate: 68.9 -> 72.2 | Improved |
| use ReCAPA hierarchical correction instead of GPT-4V | ReCAPA · AI2-THOR | coverage: 0.97 -> 0.95 | Hurt |
Closest papers by meaning
- ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning (NeurIPS 2025 · similarity 0.89)
- RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.89)
- ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents (NeurIPS 2025 · similarity 0.88)
- ATI-VLA: Action-Centric Predictive Vision–Language–Action Models via Actionable Alignment Then Adaptive Injection (NeurIPS 2026 · similarity 0.88)
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching (NeurIPS 2025 · similarity 0.88)
- Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models (NeurIPS 2026 · 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.
