paper-with-me

Papers

MemoryWAM: Efficient World Action Modeling with Persistent Memory

2026-06-18 · Sizhe Yang, Juncheng Mu, Tianming Wei, Chenhao Lu, Xiaofan Li, Linning Xu, Zhengrong Xue, Zhecheng Yuan, Dahua Lin, Jiangmiao Pang, Huazhe Xu arxiv

Robust robotic manipulation in the real world requires not only an understanding of the current observation, but also memory and dynamics modeling. World action models (WAMs) possess these capabilities by jointly modeling visual foresight and actions conditioned on both current and historical observations, making them a promising paradigm for robotic manipulation. However, existing WAMs face a fundamental trade-off: methods with efficient inference typically condition only on a bounded window of recent observations and therefore struggle in non-Markovian environments, whereas methods that preserve long histories incur time and space costs that grow substantially with sequence length. To address this challenge, we introduce MemoryWAM, a world action model with efficient persistent memory. MemoryWAM uses a hybrid memory design that combines recent frames, event-boundary anchor frames, and compact gist tokens that summarize long-range history. A tailored attention mechanism enables retrieval of both detailed short-term context and compressed long-term context, supporting memory-dependent decision-making with reduced inference latency and GPU memory usage. Across long-horizon, memory-dependent manipulation tasks in both simulation and the real world, MemoryWAM outperforms strong vision-language-action (VLA) and WAM baselines while maintaining favorable computational efficiency.

📄 PDF Abstract BibTeX arXiv:2606.20562

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation

2026-06-17 · Zirui Zheng, Jiaqian Yu, Xiongfeng Peng, jun shi 외 arxiv

Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable alternative to costly real-world experimentation by generating action-consistent video rollouts. However, persi…

Synthetic Data GenerationRobot Manipulation

AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models

2026-08-07 · Guiyu Zhao, Longteng Guo, Yanghong Mei, Zilin Zhu 외 hf

While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mou…

Spatial Reasoning

WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents

2026-06-17 · Yehang Zhang, Jianchong Su, Haojian Huang, Yifan Chang 외 arxiv

To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly evaluate language-centric retrieval and …

Question Answering

Perceptual 3D Simulation With Physical World Modeling

2026-06-25 · Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh, Jared Watrous 외 arxiv

Predicting how a scene will evolve after a desired 3D transformation from images is a central goal in vision, graphics, and robotics. Yet unlike ideal simulators with full access to 3D geometry and dynamics, real world s…

Novel View SynthesisScene Understanding

RoboStream: Weaving Spatio-Temporal Reasoning with Memory in Vision-Language Models for Robotics

2026-03-13 · Yuzhi Huang, Jie Wu, Weijue Bu, Ziyi Xiong 외 arxiv

Enabling reliable long-horizon robotic manipulation is a crucial step toward open-world embodied intelligence. However, VLM-based planners treat each step as an isolated observation-to-action mapping, forcing them to rei…