SkillFeeder › 全部 Skill › Agent工具链 › cosmos3-inference-reasoning

用一张图或一段视频,生成带推理链的多模态回答。

cosmos3-inference-reasoning

cosmos3-inference-reasoning 是 SkillFeeder 收录的Agent Skill,来自 GitHub 仓库 NVIDIA/cosmos-framework,★ 631。用一张图或一段视频,生成带推理链的多模态回答。适合多模态AI开发者。场景是Agent工具链 · Agent运行时。能做的事包括生成带<think>标签的思维链式回答、支持视频时序定位与2D图像指代、输出物理合理、具身可执行的动作规划。打开 GitHub 自行安装。

打开 GitHub

仓库
NVIDIA/cosmos-framework
仓库星标
★ 631
场景
Agent工具链 · Agent运行时
适合
多模态AI开发者
类型
Skill

能做什么

原文简介

Run the Cosmos3 Reasoner (vision-language reasoning over images and video: captioning, VQA, temporal localization, 2D grounding, describe-anything, embodied next-action and robot planning, action-CoT trajectories, physical plausibility, situation understanding) with the Edge / Nano / Super checkpoints through any of the six cookbook backends: Cosmos Framework (in-repo), vLLM server, SGLang server,

同场景推荐