
Sign up to save your podcasts
Or
本期的 5 篇论文如下:
[00:38] TOP1(🔥126) | 💡 Seed1.5-VL Technical Report(Seed1.5-VL 技术报告)
[03:11] TOP2(🔥109) | 🗣 MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder(MiniMax-Speech:具有可学习说话人编码器的内在零样本语音合成)
[05:23] TOP3(🔥86) | 💡 Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models(超越“Aha!”时刻:迈向大型推理模型中系统性元能力对齐)
[07:25] TOP4(🔥73) | 🧠 MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining(MiMo:释放语言模型的推理潜力——从预训练到后训练)
[10:04] TOP5(🔥67) | 🖼 BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset(BLIP3-o:一族完全开放的统一多模态模型——架构、训练和数据集)
【关注我们】
您还可以在以下平台找到我们,获得播客内容以外更多信息
小红书: AI速递
本期的 5 篇论文如下:
[00:38] TOP1(🔥126) | 💡 Seed1.5-VL Technical Report(Seed1.5-VL 技术报告)
[03:11] TOP2(🔥109) | 🗣 MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder(MiniMax-Speech:具有可学习说话人编码器的内在零样本语音合成)
[05:23] TOP3(🔥86) | 💡 Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models(超越“Aha!”时刻:迈向大型推理模型中系统性元能力对齐)
[07:25] TOP4(🔥73) | 🧠 MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining(MiMo:释放语言模型的推理潜力——从预训练到后训练)
[10:04] TOP5(🔥67) | 🖼 BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset(BLIP3-o:一族完全开放的统一多模态模型——架构、训练和数据集)
【关注我们】
您还可以在以下平台找到我们,获得播客内容以外更多信息
小红书: AI速递