Group 1 - The core viewpoint of the article emphasizes the development of spatial-temporal AI technology, focusing on creating intelligent systems that integrate multi-modal perception, autonomous cognition, decision-making, and precise task execution capabilities [1] - The company aims to develop a "growing digital family" companion robot for healthcare and elderly care scenarios, leveraging spatial perception, environmental understanding, and behavioral decision-making [1] - The team consists of members from prestigious institutions such as PKU, Tsinghua University, CASIA, CMU, and MBZUAI, indicating a strong academic and research foundation [1] Group 2 - The article discusses the establishment of a community called "Embodied Intelligence Heart Knowledge Planet," which serves as a platform for technical exchange in the field of embodied intelligence [4][19] - The community has created a closed loop in various fields, including industry, academia, job seeking, and Q&A exchanges, aiming to provide valuable resources and networking opportunities [6][19] - Members of the community can access a wealth of resources, including over 30 technical routes, open-source projects, and job recommendations, facilitating both entry-level and advanced learning [7][19][25] Group 3 - The community has established a job referral mechanism with multiple embodied intelligence companies, allowing members to submit their resumes for potential job opportunities [13] - Various learning paths and resources are available for beginners and those already engaged in related research, helping them to enhance their skills and knowledge in the field [14][16] - The community also hosts discussions on various topics related to robotics and embodied intelligence, providing a platform for members to seek advice and share experiences [20][78]

Core Viewpoint - The article introduces the Interleave-VLA framework, which enhances robot manipulation by utilizing interleaved image-text instructions, demonstrating significant improvements in performance over existing models [2][3][7]. Group 1: Interleave-VLA Framework - Interleave-VLA is the first framework capable of understanding interleaved image-text instructions and generating continuous action sequences in the physical world [2]. - The framework is model-agnostic and requires minimal modifications to current state-of-the-art VLA models, providing strong zero-shot generalization capabilities [2][3]. Group 2: Data Set Development - A major challenge in implementing Interleave-VLA was the lack of a large-scale interleaved embodied dataset. To address this, an automated process was developed to convert pure text instructions from the Open X-Embodiment dataset into interleaved image-text instructions [2]. - The resulting dataset contains 210,000 interaction data points and 13 million frames of images, marking the first large-scale real-world interleaved embodied dataset [2]. Group 3: Performance Evaluation - Comprehensive evaluations in simulation benchmarks and real robot experiments show that Interleave-VLA significantly enhances cross-domain generalization capabilities by 2-3 times compared to state-of-the-art baseline models [3]. - The framework supports flexible task interfaces and can handle various user-provided image instructions, such as hand-drawn sketches, in a zero-shot manner [3]. Group 4: Advantages of Interleaved Instructions - The interleaved instruction paradigm effectively utilizes heterogeneous datasets and diverse instruction images, including those sourced from the internet, showcasing its substantial scalability potential [3][7].

Group 1 - The core viewpoint of the article emphasizes the development of spatial-temporal AI technology, focusing on creating intelligent systems that integrate multi-modal perception, autonomous cognition, decision-making, and precise task execution [1] - The company aims to develop a "growth-type digital family" companion robot for healthcare and elderly care, leveraging spatial perception, environmental understanding, and behavioral decision-making [1] - The team consists of members from prestigious institutions such as PKU, Tsinghua, CASIA, CMU, and MBZUAI, indicating a strong academic foundation [1] Group 2 - The article discusses the establishment of a community called "Embodied Intelligence Heart Knowledge Planet," which serves as a platform for technical exchange in the field of embodied intelligence [4][19] - The community has created a closed loop in various fields, including industry, academia, job seeking, and Q&A exchanges, aiming to provide valuable resources and networking opportunities [6][19] - Members of the community can access cutting-edge academic content, roundtable discussions, open-source code solutions, and timely job information [7][19] Group 3 - The community has established a job referral mechanism with multiple embodied intelligence companies, facilitating connections between job seekers and potential employers [13] - Various learning paths and technical stacks have been organized for beginners and those already engaged in related research, helping them to quickly enter the field [14][16] - The community offers a wealth of resources, including open-source projects, datasets, and industry reports, to support members in their professional development [19][27][34]

点击下方 卡片 ，关注" 具身智能 之心 "公众号 作者丨 Dongming Wu等 编辑丨具身智能之心 本文只做学术分享，如有侵权，联系删文 >> 点击进入→ 具身智能之心 技术交流群 更多干货，欢迎加入国内首个具身智能全栈学习社区 ： 具身智能之心知识星球 (戳我) ， 这里包含所有你想要的。 Paper: https://arxiv.org/abs/2507.23734 写在前面：为什么"通用抓取"如此困难？ "让机器人学会抓取物体"一直是机器人领域的重要研究课题。然而，当我们把机器人从实验室的固定台面放到真实的开放世界，例如厨房、仓库、甚至马路边， 就会发现老的范式迅速失效： 一言以蔽之，机器人必须同时具备"功能推理+精细操作"两大能力。 近期，来自香港中文大学、原力灵机、中科院计算所、默罕默德·本·扎耶德人工智能大学、澳门大学等机构的研究者联合发布了全新Affordance Segmentation数据 集与模型框架，RAGNet和 AffordanceNet，旨在实现与人类指令对齐的通用抓取机器人。 二、RAGNet：面向通用抓取的大规模推理型数据集 RAGNet是一个大规模、基于推理的可供性（a ...

Group 1 - The article announces the establishment of a community focused on reinforcement learning, specifically targeting individuals working on quadrupedal, humanoid, and robotic arm control [1] - The community aims to create a platform for technical exchange and sharing within the industry [1] Group 2 - Interested individuals are encouraged to add a designated assistant on WeChat to join the group, with specific instructions for joining [2]

Core Viewpoint - The article discusses the development of AGENTSAFE, the world's first comprehensive evaluation benchmark for the safety of embodied intelligent agents, addressing the emerging risks associated with "jailbreak" attacks that can lead to dangerous actions by robots [5][12][43]. Group 1: Introduction to AGENTSAFE - AGENTSAFE is designed to fill the gap in adversarial safety evaluation for embodied agents, which have been largely overlooked in existing benchmarks [5][11]. - The research has received recognition, winning the Outstanding Paper Award at the ICML 2025 Multi-Agent Systems workshop [6]. Group 2: The Need for AGENTSAFE - Traditional AI safety concerns have focused on generating harmful content, while embodied agents can perform physical actions that pose real-world risks [10]. - The article emphasizes the importance of proactive safety measures, stating that safety vulnerabilities should be identified before any harm occurs [12]. Group 3: Features of AGENTSAFE - AGENTSAFE includes a highly realistic interactive sandbox environment, simulating 45 real indoor scenes with 104 interactive objects [14][15]. - A dataset of 9,900 dangerous commands has been created, inspired by Asimov's "Three Laws of Robotics," and includes six advanced "jailbreak" attack methods [16][20]. Group 4: Evaluation Methodology - AGENTSAFE employs an end-to-end evaluation design that assesses the entire process from perception to action execution, ensuring a comprehensive safety assessment [21][23]. - The evaluation is structured into three stages: perception, planning, and execution, with a focus on the model's ability to translate natural language commands into executable actions [31]. Group 5: Experimental Results - The study tested five mainstream vision-language models (VLMs), revealing significant performance disparities when faced with dangerous commands [30][34]. - For example, GPT-4o and GLM showed high refusal rates for harmful commands, while Qwen and Gemini had much lower refusal rates, indicating a higher susceptibility to dangerous actions [36][37]. - The results demonstrated that once commands were subjected to "jailbreak" attacks, the safety measures of all models significantly deteriorated, with GPT-4o's refusal rate dropping from 84.67% to 58.33% for harmful commands [39][43]. Group 6: Conclusion - The findings highlight the current vulnerabilities in the safety mechanisms of embodied intelligent agents, stressing the need for rigorous safety testing before deployment in real-world scenarios [43][44].

Core Insights - The article discusses the advancements in multimodal fusion and vision-language models (VLMs) as essential tools for enhancing robot vision technology, emphasizing their potential in complex reasoning and long-term task decision-making [4][10]. Multimodal Fusion and Robot Vision - Multimodal fusion enhances semantic scene understanding by integrating various data sources, such as visual, linguistic, depth, and lidar information, addressing limitations faced by traditional unimodal methods [8][9]. - The rise of VLMs has propelled the development of multimodal fusion paradigms, showcasing capabilities in zero-shot understanding and instruction following [9][10]. Key Applications and Challenges - The article identifies key applications of multimodal fusion in tasks like simultaneous localization and mapping (SLAM), 3D object detection, navigation, and robot manipulation [10][19]. - Challenges in multimodal fusion include cross-modal alignment, efficient training strategies, and real-time performance optimization [10][19]. Data Sets and Benchmarking - A comprehensive analysis of mainstream multimodal datasets used for robot tasks is provided, detailing their modality combinations, task coverage, and limitations [10][43]. - The importance of high-quality multimodal datasets is highlighted, as they are crucial for model training and performance evaluation [62]. Future Directions - The article suggests future research directions to address challenges in multimodal fusion, such as improving cross-modal alignment techniques and enhancing real-time performance [10][63]. - Emphasis is placed on the need for standardized datasets and benchmarks to facilitate comparisons across different research efforts [66].

Core Insights - The article discusses the potential of embodied intelligence technology to transform various devices and services, suggesting that if technical and data challenges are resolved, many everyday items could be "embodied" [1][2] - The future of the industry is expected to shift from autonomous driving to embodied intelligence over the next decade, creating numerous job opportunities and attracting talent from various fields [2][3] Group 1: Industry Trends - The emergence of humanoid robots and mobile operation robots in various sectors such as healthcare, industry, and home services is highlighted, indicating a growing trend in embodied applications [1][2] - The concept of "VLA" (Visual Language Action) in autonomous vehicles is introduced, suggesting that users will be able to interact with systems using natural language for navigation and task optimization [1][2] Group 2: Market Opportunities - The potential for service and industrial robots to perform multiple tasks in parallel is emphasized, which could lead to more efficient production lines without the need for extensive reconfiguration [2] - The retail and service industries are expected to see significant advancements with the introduction of autonomous robots, capable of managing large spaces like supermarkets and restaurants [2] Group 3: Community and Knowledge Sharing - The "Embodied Intelligence Knowledge Planet" has established a closed-loop system across various fields, including industry, academia, and job-seeking, to foster community engagement and knowledge sharing [4][5] - The platform offers resources such as technical routes, job information, and access to industry experts, aiming to support both newcomers and experienced professionals in the field [5][11][12] Group 4: Educational Resources - The community provides a comprehensive list of over 30 technical routes for learning, catering to different levels of expertise, from beginners to advanced researchers [17][12] - Various resources, including open-source projects, datasets, and simulation platforms, are compiled to facilitate learning and development in embodied intelligence [17][32][36]

Core Viewpoint - The article discusses the development of Spec-VLA, a speculative decoding framework designed to accelerate Vision-Language-Action (VLA) models, addressing challenges related to computational demands and decoding delays [3][4][16]. Research Background and Motivation - VLA models have shown significant progress in generating robot action sequences based on language instructions, but they face challenges such as the large parameter size of backbone Visual Language Models (VLMs) and increased decoding latency due to autoregressive decoding strategies [3]. - Existing acceleration methods have limitations, necessitating a tailored approach for VLA models [3]. Core Framework: Spec-VLA - Spec-VLA introduces a collaborative mechanism between draft and validation models to enhance inference speed, utilizing a draft model to predict action tokens and a validation model to ensure output quality [4][5]. Key Mechanism: Relaxed Acceptance - The relaxed acceptance mechanism allows for a defined threshold of acceptable distance between draft and validation model predictions, facilitating a more efficient decoding process without significant computational overhead [7][10]. Experimental Validation - The framework was evaluated on the LIBERO simulation benchmark across four task sets, demonstrating significant improvements in speed and acceptance length while maintaining success rates [9][10]. - The introduction of relaxed acceptance led to an acceleration factor of 1.22× to 1.42×, with acceptance length increasing by 25%-44% [10][11]. Key Results - The results indicate that as the relaxed threshold increases, the acceptance length significantly improves while maintaining stable success rates across various datasets [10][11]. - Case studies show that relaxed conditions reduce the number of iterations needed to complete action sequences, validating the effectiveness of the relaxed acceptance mechanism [13]. Conclusion and Limitations - Spec-VLA demonstrates the potential of speculative execution in VLA prediction tasks, achieving a speedup of 1.42× and a 44% increase in acceptance length without compromising success rates [16]. - Limitations include the lack of real-world robot scenario testing and the exploration of action chunking strategies [16].

Core Viewpoint - The article highlights the significant advancements and contributions of Daimon Robotics in the field of embodied intelligence, particularly during the WAIC 2025 event in Shanghai, showcasing their innovative technologies and collaborations with major industry players like Huawei and China Mobile [2][4][9]. Group 1: Daimon Robotics at WAIC 2025 - Daimon Robotics made a remarkable appearance at the Huawei exhibition, attracting a large audience with their instant response and low-latency performance of the Sparky 1 robot, which became a popular attraction at the event [6]. - The company showcased its groundbreaking VTLA (Visual-Tactile-Language-Action) embodied operation model, which integrates tactile perception to enhance reasoning and generalization capabilities in complex scenarios, achieving near-human dexterity [8]. Group 2: Collaborations and Industry Impact - Daimon officially joined China Mobile's embodied intelligence industry cooperation plan, aimed at promoting the productization, industrialization, and scaling of embodied intelligence technologies, alongside key partners like Yushu and Zhiyuan [9]. - The tactile perception technology is crucial for advancing robots from being merely functional to being practical and user-friendly, positioning Daimon as a representative of tactile sensing technology in the next wave of breakthroughs [9]. Group 3: Product Showcase and Technological Strength - At WAIC 2025, Daimon unveiled several core products, including the world's first multi-dimensional high-resolution tactile sensor DM-Tac W, a multi-dimensional tactile sensing dexterous hand DM-Hand1, and a wearable remote operation data collection system DM-EXton series, demonstrating the company's technological prowess and commercialization achievements [11]. - The DM-Tac W sensor is recognized as an industry benchmark for visual-tactile sensing, capable of capturing minute tactile changes, thus opening new possibilities for high-precision operational scenarios [13][14]. Group 4: Leadership in Domestic Technology - Daimon Robotics, incubated at the Hong Kong University of Science and Technology, focuses on high-resolution multi-modal tactile perception and human-centered remote operation systems, led by pioneer Professor Wang Yu in the robotics field [15]. - The company has developed the world's thinnest tactile sensor technology, overcoming challenges related to sensor thickness, computing power, and durability, and has achieved commercialization of tactile products domestically [15].