Autonomy and agency

Alibaba releases Qwen2-VL visual-agent models

Alibaba released open 2B and 7B Qwen2-VL models and a 72B API model with image, long-video, multilingual text, and visual-agent capabilities for operating mobile devices and robots from visual inputs.

CURRENT ASSESSMENT · REVISION 1
TOWARD DOOM61confidence 98/100

Why it moved the index

The release paired strong visual reasoning with explicit device and robot operation, while open weights for two tiers reduced control boundaries and the hosted 72B tier broadened high-capability access.

0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

AUDIT TRAIL

Assessment history

  1. R1
    Toward 61 · confidence 98

    New August 2024 exact visual-language and agentic model release.

    12 Aug 2026