Surprise-gated episodic memory using V-JEPA-2 improves robot QA by ≥12% over prior memory methods and outperforms supervised baselines on event segmentation.
10 From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model Lin, T., Zhang, Y ., Li, Q., Qi, H., Yi, B., Levine, S., and Malik, J
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 13roles
background 3polarities
background 3representative citing papers
DockAnywhere lifts single demonstrations to diverse docking points via structure-preserving augmentation and point-cloud spatial editing to improve viewpoint generalization in visuomotor policies for mobile manipulation.
CAMP learns a compressed behavioral memory from action history to enable success in long-horizon partially observable object manipulation without extra supervision, showing gains over baselines in real-robot and simulation tests.
EventVLA introduces foundational visual anchors and a Keyframe Evidence Memory module that predicts future keyframe probabilities from VLA embeddings to improve long-horizon task success by an average of 40% on 17 simulation and 4 real-world tasks.
SERF conditions VLA policies on online-updated neural point maps of environment and robot to improve long-horizon mobile manipulation on BEHAVIOR-1K.
DAM-VLA decouples per-modality temporal processing in vision-language-action models via latent buffers refreshed at sensor rates, achieving 95.2% average success versus 40.95% for synchronous baselines on seven real-world manipulation tasks while enabling 100 Hz control.
Adding recurrent memory tokens to VLA models raises success rates on partially observable manipulation tasks from 0.42 to 0.84 on training and 0.07 to 0.23 on held-out tasks while preserving performance under full observability.
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
TRACE attaches a trajectory-signature-indexed latent memory to existing visuomotor imitation policies to recover context for delayed-evidence branch points in long-horizon robot tasks.
The Semantic Autonomy Stack combines a seven-step parametric resolver handling 88% of instructions in under 0.1 ms with VLM escalation and a five-category cross-robot memory system, achieving 100% accuracy and 103,000-fold latency reduction on Raspberry Pi 5 robots with no GPU or training data.
BehaviorVLA learns long-horizon behavioral representations via causal Mamba encoder and phase-conditioned decoder, reporting SOTA results of 58% on RoboTwin 2.0, 98% on LIBERO, 4.36 on CALVIN, and matching OpenVLA-OFT performance with 50% data in sim-to-real transfer.
citing papers explorer
-
Worth Remembering: Surprise-Gated Robot Episodic Memory
Surprise-gated episodic memory using V-JEPA-2 improves robot QA by ≥12% over prior memory methods and outperforms supervised baselines on event segmentation.
-
DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation
DockAnywhere lifts single demonstrations to diverse docking points via structure-preserving augmentation and point-cloud spatial editing to improve viewpoint generalization in visuomotor policies for mobile manipulation.
-
Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation
CAMP learns a compressed behavioral memory from action history to enable success in long-horizon partially observable object manipulation without extra supervision, showing gains over baselines in real-robot and simulation tests.
-
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
EventVLA introduces foundational visual anchors and a Keyframe Evidence Memory module that predicts future keyframe probabilities from VLA embeddings to improve long-horizon task success by an average of 40% on 17 simulation and 4 real-world tasks.
-
SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation
SERF conditions VLA policies on online-updated neural point maps of environment and robot to improve long-horizon mobile manipulation on BEHAVIOR-1K.
-
DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model
DAM-VLA decouples per-modality temporal processing in vision-language-action models via latent buffers refreshed at sensor rates, achieving 95.2% average success versus 40.95% for synchronous baselines on seven real-world manipulation tasks while enabling 100 Hz control.
-
$\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
Adding recurrent memory tokens to VLA models raises success rates on partially observable manipulation tasks from 0.42 to 0.84 on training and 0.07 to 0.23 on held-out tasks while preserving performance under full observability.
-
PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation
PALM improves long-horizon robotic manipulation success by distilling affordance representations for object interaction and predicting within-subtask progress in a VLA model.
-
TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation
TRACE attaches a trajectory-signature-indexed latent memory to existing visuomotor imitation policies to recover context for delayed-evidence branch points in long-horizon robot tasks.
-
A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory
The Semantic Autonomy Stack combines a seven-step parametric resolver handling 88% of instructions in under 0.1 ms with VLM escalation and a five-category cross-robot memory system, achieving 100% accuracy and 103,000-fold latency reduction on Raspberry Pi 5 robots with no GPU or training data.
-
From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
BehaviorVLA learns long-horizon behavioral representations via causal Mamba encoder and phase-conditioned decoder, reporting SOTA results of 58% on RoboTwin 2.0, 98% on LIBERO, 4.36 on CALVIN, and matching OpenVLA-OFT performance with 50% data in sim-to-real transfer.
- Action-Effect Memory Pretraining for Robot Manipulation
- Gated Memory Policy: In-Context Memorization and Adaptation