He Kaiming's team proposes VISTA visual harness for multimodal agents

1 reports 1 reporting sources 6 days agoNew

Understand the event

AI overview

He Kaiming's team published VISTA, a visual-native harness that lets existing multimodal models observe environments, store raw frames outside their context, and recall, zoom in on or inspect those frames during reasoning without retraining. The team reports that paired with VISTA, Claude Opus 5.0 completed all 25 public ARC-AGI-3 games with a perfect 100 action-efficiency score, using 57.4% fewer actions than the human first-play baseline, while GPT-5.6 Sol scored 99. The team also tested VISTA on browser games, mazes and connect-the-dots tasks, and lists embodied tasks as future work.

Generated by AI from reports · Updated 6 days ago

Latest development10/11 16:59 (UTC+8)

He Kaiming team releases VISTA visual harness for multimodal reasoning 量子位

Report timeline

Follow the reports to explore different sides of the event.

10/11

16:59
量子位
He Kaiming team releases VISTA visual harness for multimodal reasoning
He Kaiming's team published VISTA, a visual-native harness that lets existing multimodal models observe environments, store raw frames outside context, and recall, zoom or inspect them during reasoning without retraining. Paired with VISTA, Claude Opus 5.0 completed all 25 public ARC-AGI-3 games with a perfect 100 action-efficiency score, using 57.4% fewer actions than the human first-play baseline, while GPT-5.6 Sol scored 99. The team also tested browser games, mazes and connect-the-dots tasks, and lists embodied tasks as future work.

Event heat trend

可比范围当前: 3
Peak within comparable coverage: 910/11 20:00 (UTC+8)
近 24 小时变化: -49%

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.

Keep reading

Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation Pipeline