MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
Summary
MemBodied introduces a fixed-size episodic memory with associative state and episode anchor to enhance vision-language-action models for history-dependent manipulation tasks, achieving significant performance improvements over baselines.
View Cached Full Text
Cached at: 09/24/26, 03:37 AM
Paper page - MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
Source: https://huggingface.co/papers/2609.28256
Abstract
Vision-Language-Actionmodelsprovideastrongfoundationforgeneral-purposerobotcontrol,yetavastmajorityofpoliciesdonotpreserveandleverageepisode-levelinformationbeyondthecurrentobservation.Thislimitationisconsequentialinhistory-dependentmanipulationtasksthatdependoninformationavailableonlyinpastobservations.Retainingpastobservationsincontextcanaidinrecoveringthisinformation,butatthesignificantcostofever-growing,bloatedcontextandinferencelatency.WethusintroduceMemBodied,afixed-sizeepisodicmemorywithtwocomplementarycomponents:anassociativestatethatrecordsinteractionsacrosspolicycallsandanepisodeanchorthatpreservesacompactrepresentationoftheinitialsceneasareference.Ateachpolicycall,themodelconditionsactiongenerationonthecurrentinputandthememorycomponents,ratherthandirectlyusingpastobservations.AcrossfiveevaluatedRMBenchtasksrequiringmemory,MemBodiedachieves7.81timesthemeansuccessrateofastatelesspolicyand2.98timesofvanillarecurrentmemory,whileoutperformingthestrongestmemory-augmentedbaselineby1.3timeswith10timesfeweraddedparameters.OnthefullyobservableLIBERO-Longsuite,itreached90.6%,a5.4%improvementoverthestatelessπ_0policy.ThesefindingssupportMemBodiedasapracticalalternativetoexpandingthepolicycontextforhistory-dependentmanipulation.
View arXiv pageView PDFProject pageGitHub1Add to collection
Get this paper in your agent:
hf papers read 2609\.28256
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.28256 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.28256 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.28256 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
LaMem-VLA proposes a latent-memory-native framework that integrates short-term and long-term historical experience directly into Vision-Language-Action reasoning, enabling better performance on long-horizon robotic manipulation tasks.
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
SimpleMemVLA introduces a simple memory mechanism for Vision-Language-Action models by feeding intact timestamped video history into a pretrained VLM backbone, achieving state-of-the-art results on long-horizon manipulation tasks without dedicated memory modules.
AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models
AtlasVLA introduces a dual-memory architecture with persistent world-ego state modeling to overcome perception and task-progress forgetting in vision-language-action models, achieving state-of-the-art long-horizon manipulation from a single wrist camera.
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
MemLens is a new benchmark for evaluating memory capabilities in large vision-language models through multi-session conversations. It compares long-context and memory-augmented approaches, revealing limitations in both and motivating hybrid architectures.
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
ComMem proposes complementary memory systems inspired by biological memory to improve test-time adaptation of vision-language models, outperforming state-of-the-art on 15 benchmarks.