AI研究論文每日精選

每日精選AI研究論文及翻譯

章魚 v4：語言模型圖
Octopus v4: Graph of language models

Wei Chen, Zhiyuan Li•Apr 30, 2024•11919

KAN：科爾莫哥洛夫-阿諾德網絡
KAN: Kolmogorov-Arnold Networks

Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Soljačić, Thomas Y. Hou, Max Tegmark•Apr 30, 2024•1133

透過多標記預測實現更好更快的大型語言模型
Better & Faster Large Language Models via Multi-token Prediction

Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve•Apr 30, 2024•783

即時家庭：遮罩式注意力用於零樣本多ID圖像生成
InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation

Chanran Kim, Jeongin Lee, Shichang Joung, Bongmo Kim, Yeul-Min Baek•Apr 30, 2024•756

迭代推理偏好優化
Iterative Reasoning Preference Optimization

Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho, He He, Sainbayar Sukhbaatar, Jason Weston•Apr 30, 2024•506

將 Llama-3 的上下文擴展十倍於一夜之間
Extending Llama-3's Context Ten-Fold Overnight

Peitian Zhang, Ninglu Shao, Zheng Liu, Shitao Xiao, Hongjin Qian, Qiwei Ye, Zhicheng Dou•Apr 30, 2024•353

MotionLCM：通過潛在一致性模型實現即時可控運動生成
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model

Wenxun Dai, Ling-Hao Chen, Jingbo Wang, Jinpeng Liu, Bo Dai, Yansong Tang•Apr 30, 2024•282

視覺事實檢查器：實現高保真度詳細標題生成
Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Yunhao Ge, Xiaohui Zeng, Jacob Samuel Huffman, Tsung-Yi Lin, Ming-Yu Liu, Yin Cui•Apr 30, 2024•254

GS-LRM：用於3D高斯點陣圖的大型重建模型
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting

Kai Zhang, Sai Bi, Hao Tan, Yuanbo Xiangli, Nanxuan Zhao, Kalyan Sunkavalli, Zexiang Xu•Apr 30, 2024•211

SAGS：結構感知 3D 高斯飄點
SAGS: Structure-Aware 3D Gaussian Splatting

Evangelos Ververas, Rolandos Alexandros Potamias, Jifei Song, Jiankang Deng, Stefanos Zafeiriou•Apr 29, 2024•141

DOCCI：相連和對比圖像的描述
DOCCI: Descriptions of Connected and Contrasting Images

Yasumasa Onoe, Sunayana Rane, Zachary Berger, Yonatan Bitton, Jaemin Cho, Roopal Garg, Alexander Ku, Zarana Parekh, Jordi Pont-Tuset, Garrett Tanzer, Su Wang, Jason Baldridge•Apr 30, 2024•131

隱形縫合：利用深度修補生成平滑的3D場景
Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

Paul Engstler, Andrea Vedaldi, Iro Laina, Christian Rupprecht•Apr 30, 2024•121

MicroDreamer：基於分數的迭代重建，在20秒內實現零樣本3D生成
MicroDreamer: Zero-shot 3D Generation in sim20 Seconds by Score-based Iterative Reconstruction

Luxi Chen, Zhengyi Wang, Chongxuan Li, Tingting Gao, Hang Su, Jun Zhu•Apr 30, 2024•101

輕平面：用於神經三維場的高度可擴展元件
Lightplane: Highly-Scalable Components for Neural 3D Fields

Ang Cao, Justin Johnson, Andrea Vedaldi, David Novotny•Apr 30, 2024•61