2024.11.14 每日AI论文 | LLMs自我改进显著,EgoVid-5M数据集创新。
Listen now
Description
本期的 7 篇论文如下: [00:26] 🤖 Large Language Models Can Self-Improve in Long-context Reasoning(大型语言模型在长上下文推理中的自我改进) [01:09] 🎥 EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation(EgoVid-5M:用于第一人称视频生成的大规模视频动作数据集) [01:58] 🔍 Direct Preference Optimization Using Sparse Feature-Level Constraints(利用稀疏特征级约束进行直接偏好优化) [02:37] 🇫 CamemBERT 2.0: A Smarter French Language Model Aged to Perfection(CamemBERT 2.0:更智能的法语语言模型,完美成熟) [03:18] 🧠 Can sparse autoencoders be used to decompose and interpret steering vectors?(稀疏自编码器能否用于分解和解释转向向量?) [03:58] 🎵 PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generation(PerceiverS:一种具有有效分割的多尺度感知器,用于长期表达性符号音乐生成) [04:39] 🎥 Motion Control for Enhanced Complex Action Video Generation(增强复杂动作视频生成的运动控制) 【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
More Episodes
本期的 8 篇论文如下: [00:28] ⚡ SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration(SageAttention2技术报告:用于即插即用推理加速的精确4比特注意力机制) [01:10] 📹 VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models(VBench++:全面且多功能的视频生成模型基准套件) [01:51] 🎮...
Published 11/21/24
本期的 7 篇论文如下: [00:33] ⚡ Continuous Speculative Decoding for Autoregressive Image Generation(自回归图像生成的连续推测解码) [01:14] 📚 RedPajama: an Open Dataset for Training Large Language Models(红睡衣:用于训练大型语言模型的开放数据集) [01:58] 🤖 Soft Robotic Dynamic In-Hand Pen Spinning(软体机器人动态手内笔旋转) [02:39] 🚀 ITACLIP: Boosting...
Published 11/20/24