Reasoning Vision-Language-Action Models

9 posts · 4 sources

NVIDIABlog4 Aug

Generate Trajectories, Reasoning Traces, and Auto-Labels with NVIDIA Alpamayo 2 Super

DeepMindBlog30 Jul

Gemini Robotics 2 brings whole body intelligence to robots

Physical IntelligenceBlog16 Apr

A Steerable Model with Emergent Capabilities

Physical IntelligenceBlog16 Dec

Emergence of Human to Robot Transfer in Vision-Language-Action Models

Physical IntelligenceBlog17 Nov

A VLA that Learns from Experience

Figure AIBlog18 Sept

Project Go-Big: Internet-Scale Humanoid Pretraining and Direct Human-to-Robot Transfer

Physical IntelligenceBlog9 Jun

Real-Time Action Chunking with Large Models

Physical IntelligenceBlog26 Feb

Teaching Robots to Listen and Think Harder

Figure AIBlog20 Feb

Helix: A Vision-Language-Action Model for Generalist Humanoid Control