MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
ACE-Brain-0.5
ACE-Brain-0.5 is an 8-billion-parameter unified embodied foundation model that integrates spatial perception, decision making, embodied interaction, self-monitoring, and self-improvement into a single closed-loop system for physical agentic AI.
Stars
36
7-day growth
No data
Forks
2
Open issues
0
License
No data
Last updated
2026-07-07
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It extends a prior spatial understanding model into a full perception-planning-action-evaluation loop using the novel SSR+ training paradigm, which combines task-vector merging with targeted fine-tuning to unify diverse robotic capabilities without cross-task interference.
Who it is for
- embodied AI researchers
- robotics engineers
- autonomous systems developers
- AI safety and monitoring researchers
Use cases
- long-horizon task planning in dynamic environments
- navigation and manipulation action generation for robots
- execution progress estimation for error recovery
- self-improvement via rollout feedback beyond static imitation
Strengths
- single 8B backbone covers five cognitive functions in a unified model
- preserves broad spatial reasoning while extending to planning and action
- SSR+ training paradigm reduces interference across grounding, navigation, manipulation, and progress estimation
- supports both executable navigation decisions and continuous manipulation control
Considerations
- trades narrow task specialization for unified coverage, which may underperform on individual benchmarks
- 8B parameter size could be computationally demanding for edge deployment
- currently only a single checkpoint and technical report are released; community adoption is nascent
README quick start
ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI
📑 Contents
🚀 News
2026/07/06: 🔥 We release our technical report and ckpt.
🧠 Introduction
ACE-Brain-0.5 is a unified embodied foundation model for Physical Agentic AI. It extends ACE-Brain-0 from an understanding-centric spatial model into a closed-loop embodied model that can perceive the physical world, plan under goals, act through robot bodies, monitor execution progress, and improve from accumulated experience.
ACE-Brain-0.5 organizes robot intelligence into five tightly coupled cognitive functions: Spatial Perception, Decision Making, Embodied Interaction, Self Monitoring, and Self Improvement. A single 8B backbone instantiates the core perception-planning-action-evaluation loop, supporting object and affordance grounding, 3D and egocentric spatial reasoning, long-horizon task planning, navigation and manipulation action generation, and progress estimation for verification and recovery.
🔥 Key Features
- Unified Embodied Foundation Model: Organizes robot intelligence into a single closed-loop model spanning Spatial Perception, Decision Making, Embodied Interaction, Self Monitoring, and Self Improvement.
- SSR+ training paradigm: Extends Scaffold-Specialize-Reconcile with a Reactivate stage, combining task-vector merging with targeted fine-tuning to unify spatial reasoning, grounding, navigation, manipulation, and progress estimation without cross-task interference.
🏗️ Method & Architecture
ACE-Brain-0.5 uses a shared embodied backbone to encode heterogeneous inputs and maintain a unified scene-and-task representation, while dedicated interfaces decode this shared state into spatial grounding, executable subgoal planning, navigation and manipulation actions, and progress-estimation signals. Training follows SSR+, which inherits the spatial scaffold from ACE-Brain-0, specializes domain capabilities, reconciles task vectors through model merging, and applies a lig
Description
The official repository of ACE-Brain-0.5 unified embodied foundation model.
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.