Skip to content
QbitAI· henry·· 2026-10-11PickAI score53

Kaiming He's team releases VISTA, a multimodal visual Harness framework

何恺明团队发布多模态Harness框架

AI summary

In the paper "VISTA: A Visual Harness for Reasoning in an Interactive World," Kaiming He's team proposes VISTA, a vision-native Harness framework that stores the raw frames returned by the environment along with animated intermediate frames outside the context, indexed by turn number and frame number, so that off-the-shelf multimodal models can use an inspect tool during inference to call up, crop, zoom in on, and compare them on demand, without training a new model.

Why it matters

Compared with existing approaches that turn the environment into a text grid, VISTA stores the raw images outside the context and looks back at them on demand, and it provides comparative data across multiple benchmarks.

Source: QbitAI · qbitai.com