`包裹,长文用`
`/`
`划分小节。 3. 列表内容用`
- `,引用用`
`,代码用`
`,重要句子可用``。
4. 保留原文所有信息,不得增删改内容。
5. 不要输出``/``/``等文档级标签。
正文内容是一段关于农业世界模型的学术新闻/摘要。原文是一段较长的段落。为了符合"长文用``/`
`划分小节"和"每个自然段落用`
`包裹",我需要将这段长文本合理地拆分成几个小节和段落,同时不改变原文的字词内容(仅通过标点、换行和HTML标签来组织)。
原文分析:
"World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest? We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested horizon of days to months, from one photo of it, its cultivar, and its camera view." -> 背景与任务介绍,可以作为第一段,加个`
`,代码用``,重要句子可用``。 4. 保留原文所有信息,不得增删改内容。 5. 不要输出``/``/``等文档级标签。 正文内容是一段关于农业世界模型的学术新闻/摘要。原文是一段较长的段落。为了符合"长文用``/`
`划分小节"和"每个自然段落用`
`包裹",我需要将这段长文本合理地拆分成几个小节和段落,同时不改变原文的字词内容(仅通过标点、换行和HTML标签来组织)。 原文分析: "World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest? We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested horizon of days to months, from one photo of it, its cultivar, and its camera view." -> 背景与任务介绍,可以作为第一段,加个`
`标题?或者直接作为引言。由于不能增删改内容,标题不能自己瞎编,除非用原文的句子作为标题,但规则说"长文用`
`/`
`划分小节",如果原文没有现成的标题,我可以不强行加标题,或者用原文的关键句作为标题。但规则4说"不得增删改内容",加标题算增内容吗?为了安全,尽量不添加原文没有的文字作为标题,或者只用原文句子。不过,通常排版可以加小标题,但如果严格"不得增删改内容",最好不添加任何原文没有的字符。那就直接用`
`分段,或者把原文拆分成几个`
`,不强行加`
`,或者将原文的某些完整句子作为`
`/`
`。 等等,规则说"长文用
/
划分小节",如果不加标题,可能不符合要求。我可以把原文中的核心句子提取出来作为标题,但这样可能会被认为"增删改"。更安全的做法是:不添加额外的标题文字,只使用`
`和``等,或者把原文按句拆分成段落。但规则明确提到"长文用
/划分小节"。我可以把原文的几句话分别作为`
`,并且不硬加标题,或者将第一句作为`
`?不,标题通常不是完整句子。
也许我可以把原文拆成几个逻辑段落,用`
`包裹,如果必须用`
`,我可以省略,因为原文没有标题。但为了遵守规则,我可以尝试用原文中的短语作为标题,但这违反了“不得增删改内容”。 再仔细看规则:"保留原文所有信息,不得增删改内容"。这意味着我不能添加任何原文没有的文字。因此,我不能自己编造`
`标题。如果原文没有标题,我就不使用`
`/`
`,或者把原文的某句话原封不动地放在`
`里?把句子放在`
`里不太合适。所以,我直接使用`
`分段,并对重要句子加``。 让我们将原文拆分为几个自然段: 段落1:World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest? 段落2:We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested horizon of days to months, from one photo of it, its cultivar, and its camera view. 段落3:In preliminary analysis, even state-of-the-art image generators get this wrong: they often grow the plant too little or give it the color and form of the wrong growth stage. We argue that they do not work out the plant's developmental state, which the photo reveals only indirectly. 段落4:We therefore propose AgroWM, which reasons about development before it draws growth. Its reasoning module, PhenoClock, works out the current growth stage, predicts the future one, and writes a Growth Script with numeric targets for height, plant area, and color; its generation module, the Rooted Renderer, then edits the photo to follow this script, adding new organs and colors to the photographed plant. 段落5:Because pixel scores can prefer an unchanged copy of the photo, we instead check each forecast's traits and developmental timing against the plant's own later photos. 段落6:On rice, 54.6% of the forecasts of AgroWM are matched to the target stage (Stage R@1), against 34.8% for GPT Image 2.5, 24.0% for Qwen Image 2.1, and 47.4% for the strongest domain-specific baseline, the same backbone fine-tuned without Growth Scripts; 9 to 20 weeks ahead, it still reaches 46.4%, against 35.7% for that baseline. 段落7:On maize, a crop with a different body plan and stage scale, the same design again scores best on all four measures. 这样拆分既保留了所有信息,又没有增删改内容,每个自然段用`
`包裹,重要名词或数据用``突出。不需要使用`
-
`、`
`、``,因为原文没有相关内容。也没有使用``/`
`,因为强行添加标题会违反“不得增删改内容”的硬性规则。 检查拆分后的文本是否完全一致: 原文:World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest? We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested horizon of days to months, from one photo of it, its cultivar, and its camera view. In preliminary analysis, even state-of-the-art image generators get this wrong: they often grow the plant too little or give it the color and form of the wrong growth stage. We argue that they do not work out the plant's developmental state, which the photo reveals only indirectly. We therefore propose AgroWM, which reasons about development before it draws growth. Its reasoning module, PhenoClock, works out the current growth stage, predicts the future one, and writes a Growth Script with numeric targets for height, plant area, and color; its generation module, the Rooted Renderer, then edits the photo to follow this script, adding new organs and colors to the photographed plant. Because pixel scores can prefer an unchanged copy of the photo, we instead check each forecast's traits and developmental timing against the plant's own later photos. On rice, 54.6% of the forecasts of AgroWM are matched to the target stage (Stage R@1), against 34.8% for GPT Image 2.5, 24.0% for Qwen Image 2.1, and 47.4% for the strongest domain-specific baseline, the same backbone fine-tuned without Growth Scripts; 9 to 20 weeks ahead, it still reaches 46.4%, against 35.7% for that baseline. On maize, a crop with a different body plan and stage scale, the same design again scores best on all four measures. 拆分并加入strong标签后:
World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest?
We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested