English(EN)SPEAR: A Simulator for Photorealistic Embodied AI Research
具身人工智能研究在接地世界模型和代理协作方面取得进展 · 跟踪了 8 个来源
作者PulseAugur 编辑部·[19 个来源]·
近期研究探讨了具身人工智能的进展，重点关注生物系统如何通过环境互动获取接地世界模型。论文讨论了将人工智能智能集成到物理机器人中的框架，例如 SPINE，旨在减少对专家校准的需求。其他研究调查了人机交互作为神经可塑性训练环境，并提出了能够从经验中学习的自演化具身代理的方法。此外，研究还检查了异构代理之间的容错协作以及通过对话对齐世界模型以改善协调。
AI
arXiv:2607.13049v1 Announce Type: new Abstract: Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven calibration. This deployment gap, the robot's spina…
arXiv cs.AI
TIER_1English(EN)·Giovanni Pezzulo, Davide Nuzzi, Marco D'Alessandro, Riccardo Proietti, Roberto Bottini, Paul Cisek·
arXiv:2607.13560v1 Announce Type: cross Abstract: Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities …
Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities create the scaffold onto which information from ot…
arXiv cs.AI
TIER_1English(EN)·Eranga Bandara, Ross Gore, Asanga Gunaratna, Ravi Mukkamala, Nihal Siriwardanagea, Gihan Siriwardanagea, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Chalani Rajapakse, Sachin Shetty, Christopher K. Rhea, Ng Wee Keong, Kasun De Zoysa, A…·
arXiv:2607.12823v1 Announce Type: new Abstract: Interaction with AI agents has become one of the most frequent activities of everyday digital life. Whether conversing with an assistant, working with a coding copilot, or generating images, the interaction follows a common iterativ…
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.0, an ef…
Interaction with AI agents has become one of the most frequent activities of everyday digital life. Whether conversing with an assistant, working with a coding copilot, or generating images, the interaction follows a common iterative loop: a request is issued, a result returned, …
arXiv:2607.10630v1 Announce Type: cross Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data. Although adversarial training offers a feasible solutio…
arXiv cs.AI
TIER_1English(EN)·Kai Yu, Lu Chen, Hanqi Li·
arXiv:2607.10811v1 Announce Type: cross Abstract: AI engineering is shifting from passive text generation by large language models (LLMs) to agent-driven task execution, creating new reliability challenges for long-horizon tasks under resource constraints and environmental uncert…
arXiv:2605.10332v2 Announce Type: replace Abstract: Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied environments vary across layouts, object states, and other execution factors, thes…
arXiv:2605.12920v3 Announce Type: replace-cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world. When agents can only partially obser…
AI engineering is shifting from passive text generation by large language models (LLMs) to agent-driven task execution, creating new reliability challenges for long-horizon tasks under resource constraints and environmental uncertainty. Conventional error-elimination optimization…
LLM-based multi-agent embodied planning remains impractical due to prohibitively high execution latency. We identify failed actions as the dominant bottleneck, stemming from two core challenges: inaccurate state tracking under partial observability and inefficient coordination th…
Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We address these limitations by introducing SPEAR: A S…
arXiv:2607.13653v1 Announce Type: new Abstract: Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged simulator states or assume complete instructions, b…
arXiv cs.CV
TIER_1English(EN)·Dayong Liu, Chao Xu, Weihong Chen, Suyu Zhang, Juncheng Wang, Jiankang Deng, Baigui Sun, Yang Liu·
arXiv:2511.18685v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spa…
Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged simulator states or assume complete instructions, bypassing realistic deployment challenges. To bri…
arXiv:2607.12894v1 Announce Type: new Abstract: Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this…
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.0, an ef…
Hacker News — AI stories ≥50 points
TIER_1English(EN)·minimaxir·
