paper-with-me

Papers

HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation

2026-06-09 · Xiaoquan Sun, Ruijian Zhang, Chen Cao, Yihan Sun, Jiahui Chen, Zetian Xu, Bo Chen, Haijier Chen, Zhen Yang, Jiarun Zhu, Yijun Hong, JingZhe Xu, Jingrui Pang, Mingqi Yuan, Jiayu Chen arxiv

World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantly enhance generalization and robustness. However, existing WAMs still struggle with task-relevant memory in long-horizon robotic manipulation. To address this, we present HiMem-WAM, a Hierarchical Memory-Gated WAM that integrates motion-centric latent actions, high-level skill latents, and boundary-triggered memory updates. Specifically, we develop a hierarchical latent action framework that jointly learns low-level motion and high-level skill latents, providing structured temporal abstraction. Meanwhile, a boundary-aware memory gate writes compact task states at predicted skill transitions, enabling causal inference without test-time generation of future video or optical flow estimation. Evaluated on LIBERO, LIBERO-PLUS, RMBench and real-world tasks, HiMem-WAM shows that hierarchical latents improve robustness under deployment perturbations, and the memory module substantially benefits memory-dependent long-horizon manipulation.

📄 PDF Abstract BibTeX arXiv:2606.10363

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow EstimationCausal Inference

Similar Papers 제목 키워드 기반

HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation

2024-11-03 · ZiRui Wang, Xinran Zhao, Simon Stepputtis, Woojun Kim 외

Understanding and predicting human actions has been a long-standing challenge and is a crucial measure of perception in robotics AI. While significant progress has been made in anticipating the future actions of individu…

Action AnticipationDecoder

HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents

2026-01-10 · Ningning Zhang, Xingxing Yang, Zhizhong Tan, Weiping Deng 외 arxiv

Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by c…

Information Extraction

HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System

2026-03-16 · Kailin Lyu, Kangyi Wu, Pengna Li, Xiuyu Hu 외 arxiv

LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods primarily rely on closed-source LLMs as navigators, which face challenges rel…

Vision-Language Navigation

Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network

2019-11-20 · Wenxiang Jiao, Michael R. Lyu, Irwin King

Real-time emotion recognition (RTER) in conversations is significant for developing emotionally intelligent chatting machines. Without the future context in RTER, it becomes critical to build the memory bank carefully fo…

Emotion RecognitionEmotion Recognition in Conversation

ActWorld: From Explorable to Interactive World Model via Action-Aware Memory

2026-06-16 · Zhexiao Xiong, Yizhi Song, Hao Kang, Qing Yan 외 arxiv

Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look ar…