Memory That Changes Action Is Not Memory That Guides It: Counterfactual Auditing of History-Conditioned Robot Policies
cs.RO
Submitted: 2026-09-23
Updated: 2026-09-23
Terminology
Sources
- ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries
- $\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
- Resolving State Ambiguity in Robot Manipulation via Adaptive Working Memory Recoding
- MEM: Multi-Scale Embodied Memory for Vision Language Action Models
- BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
- SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
- Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
- RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
- RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
- RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
- When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
- TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation
- TFP: Temporally Conditioned Memory-Fusion Policies for Visuomotor Learning
- Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation
- Gated Memory Policy: In-Context Memorization and Adaptation
- Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History
- HELM: Harness-Enhanced Long-horizon Memory for Vision-Language-Action Manipulation
- AEGIS: A Backup Reflex for Physical AI
- AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies
- MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving