• AI, But Simple
  • Posts
  • Random Attention, Flow Matching for VLAs, Tencent's Speech Foundation Model

Random Attention, Flow Matching for VLAs, Tencent's Speech Foundation Model

AI, But Simple Issue #119

Random Attention, Flow Matching for VLAs, Tencent's Speech Foundation Model

AI, But Simple Issue #119

This week, AI research landed on random attention, flow matching as the method for action generation, and an open-source model that can generate and edit speech from instructions.

We'll explain these developments and how they work visually, then take a look at some results and key movements to keep you updated in no time.

Subscribe to keep reading

This content is free, but you must be subscribed to AI, But Simple to continue reading.

Already a subscriber?Sign in.Not now