Ant Group's Robbyant Launches LingBot-VA 2.0, an Embodied-Native Video-Action World Model
SHANGHAI — Robbyant, an embodied AI company within Ant Group, today announced the release of LingBot-VA 2.0, the industry’s first embodied-native video-action worl…
Read the full articleYou might also wanna read
Robbyant: Building Embodied AI Foundation Models for Physical World AGI
Robbyant - Exploring the frontiers of embodied intelligence. We focus on foundational large models for embodied AI: LingBot-Depth (spatial p
Robbyant 蚂蚁灵波科技·2mo agoLingBot-Video: A Video Generator for Robotics
LingBot-Video has been introduced—the first open-source video generator based on the Mixture-of-Experts (MoE) architecture, optimized for em
Robbyant open-sources LingBot-World 2.0 for live video
The model can run for up to an hour at 720p and 60 frames per second, with real-time controls and multi-user interaction.
Kimi K2.5: Open-Source Multimodal AI Model with Visual Agentic Intelligence and Agent Swarm Capabilities
Kimi K2.5 defines Visual Agentic Intelligence. Trained on 15T tokens, it introduces SOTA visual coding and autonomous agent swarm. Read the
Ant Group Unveils R1 Humanoid Robot as Competitor to Tesla's Optimus
Robbyant had the slow-moving robot potter around the kitchen at tech fairs in Berlin and Shanghai.
The Verge·10mo ago蚂蚁灵波科技开源实时交互世界模型LingBot-World 2.0
36氪获悉，蚂蚁灵波科技宣布开源新一代实时交互世界模型LingBot-World 2.0。该模型全面升级世界预测与交互能力，支持小时级实时生成、720p/60fps高清实时输出以及更丰富的交互动作与事件，并在业界首次将Agent机制引入世界模型。LingBot-World 2.0
Comments
Sign in to join the conversation.
No comments yet. Be the first.