AIBase
Home
AI NEWS
AI Tools
GEO & AEO
MCP
AI Models
AI Marketplace
EN

AI News

View More

World Models Enter the Physical World: Antlingbot Opens Source LingBot-VA, Allowing Robots to Think Before Acting

Ant Group's LingBot-VA, an open-source embodied world model, introduces an autoregressive video-action framework that integrates video generation with robotic control. It simultaneously predicts future states and outputs action sequences, enabling real-time planning and execution. Real-world tests confirm its effectiveness in complex physical interaction tasks.....

16.2k 4 hours ago
World Models Enter the Physical World: Antlingbot Opens Source LingBot-VA, Allowing Robots to Think Before Acting

Models

View More

Claude Opus 4

Anthropic

Claude Opus 4

$105

Input tokens/M

$525

Output tokens/M

200

Context Length

Pangu-RAG-N1-32K-4.3.2

Huawei

Pangu-RAG-N1-32K-4.3.2

-

Input tokens/M

-

Output tokens/M

32

Context Length

DeepSeek-R1-Distill-Qwen-14B

Deepseek

DeepSeek-R1-Distill-Qwen-14B

$2

Input tokens/M

-

Output tokens/M

8

Context Length

Gemini 2.0 Flash Thinking

Google

Gemini 2.0 Flash Thinking

-

Input tokens/M

-

Output tokens/M

-

Context Length

MiniMax Hailuo-02 512P

Minimax

MiniMax Hailuo-02 512P

-

Input tokens/M

-

Output tokens/M

-

Context Length

AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAIBaseLLM LeaderboardAI Ranking
© 2026AIBase
Business CooperationSite Map