AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: Embodied AI
29 article(s) found · Clear tag
SCAIL-2 – Zhipu AI and Tsinghua's Open-Source Character Animation Model
SCAIL-2 is the second-generation film-grade character animation framework open-sourced jointly by Zhipu AI and Professor Liu Yongjin's research group at Tsinghua University. Built on a Diffusion Trans...
Qwen-VLA – Alibaba Tongyi's General Vision-Language-Action Model
Qwen-VLA is Tongyi Lab's general vision-language-action model: Qwen3.5-4B VLM backbone plus 1.15B DiT action decoder. A unified action trajectory prediction framework merges manipulation, navigation, ...
Qwen-Robot Suite – Alibaba Tongyi's Physical-World Foundation Model Suite
Qwen-Robot Suite is Alibaba Tongyi Lab's foundation model suite for physical-world intelligence, comprising Qwen-RobotNav (navigation), Qwen-RobotManip (manipulation), and Qwen-RobotWorld (world model...
Microsoft Scout – Microsoft's AI Personal Assistant
Microsoft Scout is an enterprise-grade AI personal assistant from Microsoft. It is not a traditional chatbot but an Autopilot agent built on the OpenClaw open-source stack with its own Entra identity....
Kairos-HomeWorld – Daxiao Robotics' Whole-Home 3D Interactive World Model
Kairos-HomeWorld is the world's first whole-home 3D interactive world model, jointly released by Daxiao Robotics with The Chinese University of Hong Kong and Shenzhen Hetao Institute. Through an innov...
Cosmos 3 – NVIDIA's Open-Source Full-Modality Physical AI Foundation Model
Cosmos 3 is NVIDIA's first fully open-source, full-modality physical AI foundation model. Built on an innovative hybrid Transformer architecture, it natively fuses visual reasoning, world generation, ...
Nextie Alpha – The Industry's First Cognitive Model from Nextie
Nextie Alpha (NextieAlpha) is the industry's first cognitive model from Nextie, led by Li Di ("father of Xiaoice"). At only 4B parameters, it deploys on edge devices. Built on open-source reasoning mo...
ACE-Ego – Open Embodied Manipulation VLA from ACERobotics and CUHK
ACE-Ego is an open one-brain-multi-embodiment manipulation VLA model co-developed by ACERobotics (大晓机器人) and CUHK MMLab. Pretrained on 6.0K+ hours of egocentric human video, it uses camera-space actio...
ABot-Earth 0.5 – Amap's World's First 3D-Native Urban World Model
ABot-Earth 0.5 is the world's first 3D-native urban world model from Amap, part of Alibaba Group. Positioned as an automated 3D city factory, it lets users input a single satellite image or a text des...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.