UBTECH introduces Thinker-WM, unifying video, depth, and robot actions in one world model

What happened

UBTECH introduces Thinker-WM, a multimodal world model that jointly models RGB video, depth, and robot actions through a shared Unified Dynamics Transformer. In material supplied by UBTECH and republished by QbitAI, the company reports leading results on WorldOlympiad, EWMBench, and WorldArena1.0 Track-1, including scores of 0.740 on WorldOlympiad and 4.66 on EWMBench. The model supports six capability modes through shared weights, and adding depth improved RoboTwin single-task success by 15 percentage points over a baseline without depth.

The story so far

UBTECH introduced Thinker-WM, a world model that jointly models RGB video, depth, and robot actions, and reported first-place results on WorldOlympiad, EWMBench, and WorldArena1.0 Track-1. In company-supplied material republished by QbitAI, UBTECH reported scores of 0.740 on WorldOlympiad and 4.66 on EWMBench. Thinker-WM uses a shared Unified Dynamics Transformer and supports six capability modes with shared weights. UBTECH also reported that adding depth improved single-task success on RoboTwin by 15 percentage points compared with a baseline without depth.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights