Hugging Face Trending Papers

SPIRE: Task-agnostic embodied continual learning through autonomous situation inference and causal motor-primitive reuse

arXiv Machine Learning
Nov 2

When the Past Shapes Action: Understanding Embodied Memory

The paper "When the Past Shapes Action: Understanding Embodied Memory" surveys how embodied AI agents can preserve and use past observations, actions, and experiences to improve decision-making in dynamic environments. It categorizes existing approaches along six memory requirements—world-state persistence, task progress, belief maintenance, experiential learning, etc.—and eight architectural styles such as recurrent states, fast weights, and spatial memory. The authors evaluate how current benchmarks test memory-dependent behavior and highlight open challenges in selecting relevant experiences, maintaining consistent beliefs, and consolidating knowledge across episodes.

By Siqi Li, Ziyi Bai, Xinrun Xu, Tinglei Huang, B\"orje F. Karlsson
arXiv AI
Oct 5

RIFAR: Reliability and Forgetting-Aware Replay for Continual Robot Learning

RIFAR is a new continual learning method for robots that uses reliability screening and drift-aware replay to mitigate forgetting while keeping storage low. It reconstructs past trajectories from short demonstration prefixes and employs a frozen inverse-dynamics model to verify action‑visual consistency. In experiments on LIBERO suites and real‑world tasks, RIFAR outperforms previous generative replay approaches, achieving high performance with only a small fraction of stored steps.

By Zirong Song, Zheng Lu, Haoran Liao, Wanqi Zhong, Yunhe Ni, Lijie Wang, Xiuying Chen
arXiv AI
Jun 3

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

arXiv:2605. 27762v2 Announce Type: replace Abstract: We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience.

By Yuchen Guo, Junli Gong, Weicheng Wang, Hongmin Cai, Yiu-ming Cheung, Weifeng Su
arXiv AI
Aug 7

SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation

arXiv:2608. 05970v1 Announce Type: cross Abstract: Embodied visuomotor models, including Diffusion Policy (DP) and Vision-Language-Action (VLA) models, have demonstrated promising performance on robotic manipulation benchmarks.

By Changyuan Wang, Chubin Zhang, Zhenyu Wu, Runhao Li, Angyuan Ma, Ke Chao, Yinan Liang, Xiuwei Xu, Ziwei Wang, Yansong Tang, Jiwen Lu
Hugging Face Trending Papers
Oct 13

ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models

ACCRUE is a continual off‑policy reinforcement learning framework designed for robot foundation models. It keeps lightweight actor and critic networks across tasks, reusing behavioral and value knowledge from previous RL stages while preserving prior behavior through actor distillation on a small set of retained episodes. Experiments on contact‑rich assembly tasks in simulation and on real robots show that ACCRUE speeds up learning of new tasks, nearly eliminates forgetting, and cuts real‑robot training time by 31.0% to 68.5%.

arXiv Machine Learning
Jun 2

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

arXiv:2603. 11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments.

By Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone, Roberto Martin-Martin
arXiv Machine Learning
Sep 21

Benchmarking World Models for Continual Learning on Compositional Tasks

The paper introduces a compositional continual learning benchmark for world models in robot manipulation, designed to isolate knowledge reuse from learning speed and capacity. Tasks are curated to combine previously seen action and perception components, allowing analysis of how different modalities affect reuse. Experiments show that modular world models better balance reuse and forgetting than conventional methods, yet none fully solve the challenge, highlighting the need for models explicitly built to reuse knowledge without forgetting.

By Haoyu Zhou, Joe Watson, Anson Lei, Ingmar Posner