Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
AI 周报 W20：可解释性 / Agent 商业化 / 本地部署 / 多模态 RAG
Published:
本周 Top 10 速览：可解释性、Agent 商业化、本地部署、多模态 RAG、Tool Calling 蒸馏、VLA 部署、人形机器人协作。
小米 MiMo-V2.5：100万 token 上下文，比 Claude 便宜 10 倍
Published:
小米发布 MiMo-V2.5，310B 参数的稀疏 MoE 模型，激活参数只有 15B，推理成本接近一个小模型，能力是旗舰级别的。原生支持图片和音频输入，上下文最长 100 万 token，权重完整开源在 HuggingFace。
京东 JoyAI-RA：人类视频终于不再只是机器人论文里的陪衬数据
Published:
JoyAI-RA 最值得看的地方，不是它在 RoboCasa GR1 Tabletop 上拿了 63.2%，而是京东把一件很多人都知道难、但一直没真做通的事往前推了一步：人类操作视频，终于不再只是机器人论文里的陪衬数据。
GR00T N1.7：VLM backbone 换了三次，每次在解什么问题
Published:
GR00T N1.7 刚发布，最值得看的改动是 VLM backbone：从 N1.6 的内部 Cosmos-2B 换成了 Cosmos-Reason2-2B。这已经是 N1 系列第三次换 backbone 了。
PI π0.7：机器人基础模型首次出现组合泛化
Published:
π0.7 做到了一件之前没有机器人模型做过的事：把训练时见过的技能拼在一起，解决训练时从没出现过的新任务。这个能力叫组合泛化。LLM 早就有了，机器人没有——直到现在。
Gemini Robotics-ER 1.6：谷歌机器人大脑的空间推理大幅升级
Published:
谷歌 DeepMind 发布了 Gemini Robotics-ER 1.6，「具身推理」系列模型的重大升级。核心问题：让机器人从「能动」变成「看懂」——看懂空间关系，看懂任务完没完成，知道什么时候不该动。
GEN-1：机器人部署门槛首次被跨越
Published:
Generalist AI 发布了 GEN-1，核心主张是：把成功率做到 99%+，跨过工厂采购自动化方案的隐性门槛。低于这个线，一条流水线每小时要人工干预多次，自动化就失去意义。之前整个行业卡在 64%–81%，GEN-1 是第一个跨过这条线的。
雷军亲自下场：小米 AI 人才专项计划，未来三年投入 600 亿
Published:
雷军在微博亲自官宣：小米正式启动 AI 人才专项招募计划，面向全球招募 AI 顶尖人才。招募同步开放三个阶段：应届生、实习生、社会招聘，不限地域。
LAP：用语言统一动作表示，首个实现跨本体零样本迁移的 VLA
Published:
Princeton + Physical Intelligence 最近出了篇论文，解决了一个困扰具身智能很久的问题——机器人策略跨本体迁移。
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Developing Real-Time Scheduling Policy by Deep Reinforcement Learning
Published in 27th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2021
Authors: Zitong Bo, Ying Qiao, Chang Leng, Hongan Wang, Chaoping Guo and Shaohui Zhang
Recommended citation: BO, Zitong, et al. Developing real-time scheduling policy by deep reinforcement learning. In: 2021 IEEE 27th Real-Time and Embedded Technology and Applications Symposium (RTAS). IEEE, 2021. p. 131-142.
Download Paper
HFGCN: Hybrid Filter Graph Convolutional Network for Heterophilic Graphs
Published in 2024 International Conference on Intelligent Computing (ICIC), 2024
Authors: Zitong Bo, Chaoyi Yang, Yilin Li, Kaiyue Xu, Ying Qiao, Chang Lengand Hongan Wang
Recommended citation: BO, Zitong, et al. HFGCN: Hybrid Filter Graph Convolutional Network for Heterophilic Graphs. In: International Conference on Intelligent Computing. Singapore: Springer Nature Singapore, 2024. p. 439-450.
Download Paper
Designing Real-Time Neural Networks by Efficient Neural Architecture Search
Published in 2024 International Conference on Intelligent Computing (ICIC), 2024
Authors: Zitong Bo, Yilin Li, Ying Qiao, Chang Leng and Hongan Wang
Recommended citation: BO, Zitong, et al. Designing Real-Time Neural Networks by Efficient Neural Architecture Search. In: International Conference on Intelligent Computing. Singapore: Springer Nature Singapore, 2024. p. 62-73.
Download Paper
RTDeepEnsemble: Real-time DNN Ensemble Method for Machine Perception Systems
Published in The 42nd IEEE International Conference on Computer Design (ICCD), 2024
Authors: Zitong Bo, Chaoping Guo, Chang Leng, Ying Qiao and Hongan Wang
I will make a presentation in Milan, Italy on November 18
Recommended citation:
Download Paper
Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
Published in arXiv preprint, 2025
Authors: Zitong Bo, Yue Hu, Jinming Ma, Mingliang Zhou, Junhui Yin, Yachen Kang, Yuqi Liu, Tong Wu, Diyun Xiang, Hao Chen
Recommended citation: Bo, Z., Hu, Y., Ma, J., Zhou, M., Yin, J., Kang, Y., Liu, Y., Wu, T., Xiang, D., & Chen, H. (2025). Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation. arXiv preprint arXiv:2509.25852.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.