4zhvml8 发表于 2024-10-10 06:52:31

MicroAgents：持有自我编辑能力的智能代理；多媒介资源生成工具


    <h1 style="color: black; text-align: left; margin-bottom: 10px;">1. MicroAgents：<span style="color: black;">拥有</span>自我编辑功能的智能代理</h1>
    <div style="color: black; text-align: left; margin-bottom: 10px;"><img src="https://p3-sign.toutiaoimg.com/tos-cn-i-axegupay5k/689c879e6e9945e7956723ce1f9f4847~noop.image?_iz=58558&amp;from=article.pc_detail&amp;lk3s=953192f4&amp;x-expires=1728785583&amp;x-signature=kq%2BU89W69MDuej%2FKpBXFc5ZthEU%3D" style="width: 50%; margin-bottom: 20px;"></div>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;"><span style="color: black;">近期</span>，GitHub上发布了一个名为Microagents的新项目，它是一种能够自我编辑其提示和Python代码的代理。这个项目旨在<span style="color: black;">帮忙</span><span style="color: black;">研发</span>人员更<span style="color: black;">容易</span>地创建、测试和<span style="color: black;">安排</span>人工智能代理，而无需进行繁琐的手动编程。Microagents项目<span style="color: black;">运用</span>Python<span style="color: black;">做为</span><span style="color: black;">重点</span>编程语言，并<span style="color: black;">供给</span>了一组API来<span style="color: black;">帮忙</span><span style="color: black;">研发</span>人员快速创建自己的代理。例如，<span style="color: black;">运用</span>Microagents，<span style="color: black;">研发</span>人员<span style="color: black;">能够</span><span style="color: black;">容易</span>创建一个代理，该代理<span style="color: black;">能够</span>自动回答<span style="color: black;">平常</span>的问题，<span style="color: black;">或</span><span style="color: black;">按照</span>用户输入生成文本。<span style="color: black;">另外</span>，Microagents还<span style="color: black;">准许</span>代理自学习，并<span style="color: black;">按照</span>它们所处的环境进行自我<span style="color: black;">调节</span>。该项目<span style="color: black;">已然</span>得到了广泛的关注，其创新性和实用性在人工智能<span style="color: black;">行业</span><span style="color: black;">导致</span>了巨大的兴趣。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">Microagents是一种能够自我编辑其提示和Python代码的代理。</span></span><span style="color: black;"><span style="color: black;">Microagents项目<span style="color: black;">运用</span>Python<span style="color: black;">做为</span><span style="color: black;">重点</span>编程语言，并<span style="color: black;">供给</span>了一组API来<span style="color: black;">帮忙</span><span style="color: black;">研发</span>人员快速创建自己的代理。</span></span><span style="color: black;"><span style="color: black;">该项目<span style="color: black;">已然</span>得到了广泛的关注，其创新性和实用性在人工智能<span style="color: black;">行业</span>引起了巨大的兴趣。</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">Microagents</span>, <span style="color: black;">人工智能代理</span>, <span style="color: black;">Python编程</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/1</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">2. Amphion-开源多<span style="color: black;">媒介</span>资源生成工具包</h1>
    <div style="color: black; text-align: left; margin-bottom: 10px;"><img src="https://p3-sign.toutiaoimg.com/tos-cn-i-qvj2lq49k0/fac381b28759440aab9b62dd83243198~noop.image?_iz=58558&amp;from=article.pc_detail&amp;lk3s=953192f4&amp;x-expires=1728785583&amp;x-signature=xLpx2HBAv8K5bcD9tQ%2FFLm9u9tw%3D" style="width: 50%; margin-bottom: 20px;"></div>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">Amphion是一款新的<span style="color: black;">媒介</span>生成工具包，支持音乐和语音，并且团队正在<span style="color: black;">奋斗</span>添加<span style="color: black;">更加多</span>的模型。该工具包基于开源技术，可自由<span style="color: black;">运用</span>和修改。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">Amphion是一款新的<span style="color: black;">媒介</span>生成工具包</span></span><span style="color: black;"><span style="color: black;">支持音乐和语音</span></span><span style="color: black;"><span style="color: black;">基于开源技术，可自由<span style="color: black;">运用</span>和修改</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;"><span style="color: black;">媒介</span>生成</span>, <span style="color: black;">开源技术</span>, <span style="color: black;">音乐和语音</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/2</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">3. 基于UNet编码器实现更快的扩散模型</h1>
    <div style="color: black; text-align: left; margin-bottom: 10px;"><img src="https://p3-sign.toutiaoimg.com/tos-cn-i-qvj2lq49k0/ec45ae3b6973475a98df1f8290e434b5~noop.image?_iz=58558&amp;from=article.pc_detail&amp;lk3s=953192f4&amp;x-expires=1728785583&amp;x-signature=ahb2UiwYEiG6WqJY5ibRWy6fjUI%3D" style="width: 50%; margin-bottom: 20px;"></div>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;"><span style="color: black;">近期</span>的一项<span style="color: black;">科研</span><span style="color: black;">显示</span>，与解码器相比，<span style="color: black;">运用</span>UNet编码器在扩散模型中表现更加稳定。这一<span style="color: black;">发掘</span><span style="color: black;">引起</span>了一种新的编码器传播<span style="color: black;">方法</span>，<span style="color: black;">明显</span>加快了文本到图像和文本到视频生成等任务的速度。该<span style="color: black;">科研</span>成果已在GitHub上发布。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;"><span style="color: black;">运用</span>UNet编码器在扩散模型中表现更加稳定</span></span><span style="color: black;"><span style="color: black;">新的编码器传播<span style="color: black;">方法</span><span style="color: black;">明显</span>加快了文本到图像和文本到视频生成等任务的速度</span></span><span style="color: black;"><span style="color: black;"><span style="color: black;">科研</span>成果已在GitHub上发布</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">扩散模型</span>, <span style="color: black;">UNet编码器</span>, <span style="color: black;">GitHub</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/3</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">4. Google Vision开源权重分片，<span style="color: black;">提高</span>多节点系统训练效率</h1>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">Google的Big Vision项目是一个<span style="color: black;">科研</span>和生产最先进的视觉系统的重要工具库。<span style="color: black;">近期</span>，<span style="color: black;">她们</span>添加了权重分片，使得在多节点系统上的训练更加容易。这个新功能<span style="color: black;">能够</span>将模型分成多个子模型，分别在<span style="color: black;">区别</span>的节点上进行训练，最后再将它们组合在<span style="color: black;">一块</span>。这<span style="color: black;">极重</span>地<span style="color: black;">加强</span>了训练的效率，减少了训练时间。Big Vision项目的开源代码<span style="color: black;">已然</span>发布在GitHub上，为视觉<span style="color: black;">行业</span>的<span style="color: black;">科研</span>人员和<span style="color: black;">研发</span>者<span style="color: black;">供给</span>了很好的<span style="color: black;">帮忙</span>。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">Google Big Vision项目添加权重分片功能，方便多节点系统训练</span></span><span style="color: black;"><span style="color: black;">新功能将模型分成多个子模型，在<span style="color: black;">区别</span>节点上进行训练</span></span><span style="color: black;"><span style="color: black;">训练效率大大<span style="color: black;">加强</span>，节省训练时间</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">Google</span>, <span style="color: black;">Big Vision</span>, <span style="color: black;">视觉系统</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/4</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">5. 比尔盖茨，2024年标志着道路的转折点</h1>
    <div style="color: black; text-align: left; margin-bottom: 10px;"><img src="https://p3-sign.toutiaoimg.com/tos-cn-i-qvj2lq49k0/40caaa63fb704faeaddd2afbec8e4656~noop.image?_iz=58558&amp;from=article.pc_detail&amp;lk3s=953192f4&amp;x-expires=1728785583&amp;x-signature=jayiTY1Khmqd%2BxhjuNRpfwQFZrg%3D" style="width: 50%; margin-bottom: 20px;"></div>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">2023年标志着新时代的<span style="color: black;">起始</span>，2024年是塑造世界下一个更好篇章的机遇。这一年向<span style="color: black;">咱们</span>展示了人工智能<span style="color: black;">怎样</span>塑造<span style="color: black;">将来</span>。该技术将被用于<span style="color: black;">帮忙</span>改善<span style="color: black;">咱们</span>生活的许多方面，并减少世界各地的不平等。虽然当前依然面临着挑战，但<span style="color: black;">将来</span>依然充满<span style="color: black;">期盼</span>，<span style="color: black;">由于</span>创新的速度从未如此之快。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">2024年标志着一个新的时代的到来</span></span><span style="color: black;"><span style="color: black;">人工智能将被用于<span style="color: black;">帮忙</span>改善<span style="color: black;">咱们</span>生活的许多方面</span></span><span style="color: black;"><span style="color: black;">创新的速度从未如此之快</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">人工智能</span>, <span style="color: black;">创新</span>, <span style="color: black;"><span style="color: black;">将来</span></span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/5</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">6. 论文：图神经网络为节点<span style="color: black;">归类</span><span style="color: black;">供给</span>更好的<span style="color: black;">处理</span><span style="color: black;">方法</span></h1>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;"><span style="color: black;">科研</span>人员<span style="color: black;">研发</span>了一种名为DSF的新<span style="color: black;">办法</span>，以改进谱图神经网络。<span style="color: black;">经过</span>引入节点特定的过滤器权重，DSF<span style="color: black;">能够</span>更好地处理像万维网<span style="color: black;">这般</span>的<span style="color: black;">繁杂</span>网络。谱图神经网络（SGNN）是一种基于图的深度学习<span style="color: black;">办法</span>，它在节点<span style="color: black;">归类</span>、图<span style="color: black;">归类</span>和节点嵌入等任务上<span style="color: black;">已然</span>取得了很好的结果。然而，SGNN存在<span style="color: black;">有些</span>问题，如过度依赖输入图的拉普拉斯矩阵，以及对权重共享的限制。为<span style="color: black;">认识</span>决这些问题，研究人员提出了一个新的<span style="color: black;">办法</span>，<span style="color: black;">叫作</span>为DSF，它<span style="color: black;">运用</span>特定于节点的过滤器权重来改善SGNN，从而更好地处理<span style="color: black;">繁杂</span>网络。DSF的性能与现有<span style="color: black;">办法</span>相比有所<span style="color: black;">加强</span>，<span style="color: black;">尤其</span>是在处理大规模图像万维网<span style="color: black;">这般</span>的大型网络时。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">DSF是一种新的<span style="color: black;">办法</span>，用于改进谱图神经网络</span></span><span style="color: black;"><span style="color: black;">它<span style="color: black;">运用</span>节点特定的过滤器权重来更好地处理<span style="color: black;">繁杂</span>网络</span></span><span style="color: black;"><span style="color: black;">DSF的性能比现有<span style="color: black;">办法</span>更好，<span style="color: black;">尤其</span>是在处理大型网络时</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">图神经网络</span>, <span style="color: black;">节点<span style="color: black;">归类</span></span>, <span style="color: black;">DSF</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/6</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">7. 论文：SmooSeg，更优越的语义分割技术</h1>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">本<span style="color: black;">科研</span>介绍了SmooSeg，这是一种新的<span style="color: black;">办法</span>，利用了图像中相邻特征<span style="color: black;">常常</span>共享<span style="color: black;">类似</span>含义的原则。SmooSeg的<span style="color: black;">重点</span>优点是<span style="color: black;">加强</span>了图像分割的准确性和速度。<span style="color: black;">经过</span>在训练过程中<span style="color: black;">思虑</span>相邻特征之间的关系，SmooSeg能够更好地理解图像的语义信息。<span style="color: black;">另外</span>，SmooSeg还采用了一种新的<span style="color: black;">办法</span>来处理边界像素，从而进一步<span style="color: black;">加强</span>了分割的精度。该技术在图像分割<span style="color: black;">行业</span><span style="color: black;">拥有</span>广泛的应用前景。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">SmooSeg是一种新的图像分割<span style="color: black;">办法</span>，利用了相邻特征共享<span style="color: black;">类似</span>含义的原则</span></span><span style="color: black;"><span style="color: black;">SmooSeg<span style="color: black;">经过</span><span style="color: black;">思虑</span>相邻特征之间的关系来<span style="color: black;">加强</span>图像分割的准确性和速度</span></span><span style="color: black;"><span style="color: black;">该技术在图像分割<span style="color: black;">行业</span><span style="color: black;">拥有</span>广泛的应用前景</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">图像分割</span>, <span style="color: black;">语义分割</span>, <span style="color: black;">SmooSeg</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/7</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">8. 法律科技与AI：Lightspeed的观点</h1>
    <div style="color: black; text-align: left; margin-bottom: 10px;"><img src="https://p3-sign.toutiaoimg.com/tos-cn-i-qvj2lq49k0/86bbb8e1815146eba9c07c0703d09794~noop.image?_iz=58558&amp;from=article.pc_detail&amp;lk3s=953192f4&amp;x-expires=1728785583&amp;x-signature=C8vyryiu6JFc3HV%2FWWslO1CaZ7A%3D" style="width: 50%; margin-bottom: 20px;"></div>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">Lightspeed对法律科技<span style="color: black;">行业</span>与人工智能的观点非常有趣，透明度很高，从VC的<span style="color: black;">方向</span>来看对所有人都有好处。<span style="color: black;">她们</span><span style="color: black;">供给</span>了<span style="color: black;">有些</span>有趣的见解，<span style="color: black;">仅有</span>时间能证明<span style="color: black;">她们</span><span style="color: black;">是不是</span>正确。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">Lightspeed<span style="color: black;">供给</span>了法律科技<span style="color: black;">行业</span>与人工智能的观点</span></span><span style="color: black;"><span style="color: black;"><span style="color: black;">她们</span>的观点透明度很高</span></span><span style="color: black;"><span style="color: black;"><span style="color: black;">仅有</span>时间能证明<span style="color: black;">她们</span><span style="color: black;">是不是</span>正确</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">法律科技</span>, <span style="color: black;">人工智能</span>, <span style="color: black;"><span style="color: black;">危害</span>投资</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/8</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">9. 斯坦福发布新序列混合器</h1>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">Mamba的创建者（以及许多其他模型）发布了一篇很专业的博客文章，概述了基本的序列混合架构，相<span style="color: black;">针对</span>标准Transformer，<span style="color: black;">能够</span><span style="color: black;">得到</span>相当大的速度<span style="color: black;">提高</span>。该团队的新模型<span style="color: black;">运用</span>了这种混合<span style="color: black;">办法</span>，并且<span style="color: black;">得到</span>了非常好的性能。这种新架构可能会对自然语言处理模型的<span style="color: black;">将来</span>产生深远的影响。</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">划重点</h1><span style="color: black;"><span style="color: black;">新模型<span style="color: black;">运用</span>基本序列混合架构，<span style="color: black;">得到</span>了非常好的性能。</span></span><span style="color: black;"><span style="color: black;">相<span style="color: black;">针对</span>标准Transformer，该混合方法<span style="color: black;">能够</span><span style="color: black;">得到</span>相当大的速度<span style="color: black;">提高</span>。</span></span><span style="color: black;"><span style="color: black;">这种新架构可能会对自然语言处理模型的<span style="color: black;">将来</span>产生深远的影响。</span></span>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">标签：</span><span style="color: black;">序列混合器</span>, <span style="color: black;">自然语言处理</span>, <span style="color: black;">深度学习</span></span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><strong style="color: blue;"><span style="color: black;">原文链接见文末/9</span></strong></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">每日AIGC</h1>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">关注「</span><strong style="color: blue;"><span style="color: black;">漫话<span style="color: black;">研发</span>者</span></strong>」，精选<span style="color: black;">全世界</span>AI前沿科技<span style="color: black;">新闻</span>以及高质量AI开源工具，帮你给<span style="color: black;">每日</span>AI前沿划重点！</span></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"><span style="color: black;"><span style="color: black;">- END -</span></span></span></p>
    <h1 style="color: black; text-align: left; margin-bottom: 10px;">参考资料</h1>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/1:</span><span style="color: black;">https://github.com/aymenfurter/microagents?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/2: </span><span style="color: black;">https://github.com/open-mmlab/Amphion?s=09&amp;%3Butm_source=9527ai&amp;utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/3: </span><span style="color: black;">https://github.com/hutaihang/faster-diffusion?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/4: </span><span style="color: black;">https://github.com/google-research/big_vision?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/5: </span><span style="color: black;">https://www.gatesnotes.com/The-Year-Ahead-2024?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/6:</span><span style="color: black;">https://arxiv.org/abs/2312.09041v1?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/7: </span><span style="color: black;">https://arxiv.org/abs/2310.17874v1?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/8:</span><span style="color: black;">https://lsvp.com/legaltech-x-ai-the-lightspeed-view/?utm_source=talkingdev.uwl.me</span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;"></span></p>
    <p style="font-size: 16px; color: black; line-height: 40px; text-align: left; margin-bottom: 15px;"><span style="color: black;">原文链接见文末/9: </span><span style="color: black;">https://hazyresearch.stanford.edu/blog/2023-12-11-zoology2-based?utm_source=talkingdev.uwl.me</span></p>




页: [1]
查看完整版本: MicroAgents：持有自我编辑能力的智能代理；多媒介资源生成工具