AI研究論文每日精選

每日精選AI研究論文及翻譯

深化 LLM 思維的演進
Evolving Deeper LLM Thinking

Kuang-Huei Lee, Ian Fischer, Yueh-Hua Wu, Dave Marwood, Shumeet Baluja, Dale Schuurmans, Xinyun Chen•Jan 17, 2025•1145

ComplexFuncBench：在長文本情境下探索多步驟和受限函數調用
ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario

Lucen Zhong, Zhengxiao Du, Xiaohan Zhang, Haiyi Hu, Jie Tang•Jan 17, 2025•202

GaussianAvatar-Editor：逼真可動的高斯頭像編輯器
GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor

Xiangyue Liu, Kunming Luo, Heng Li, Qi Zhang, Yuan Liu, Li Yi, Ping Tan•Jan 17, 2025•62

在醫療保健領域搭建語言障礙的橋樑：一項關於阿拉伯語LLM的研究。
Bridging Language Barriers in Healthcare: A Study on Arabic LLMs

Nada Saadi, Tathagata Raha, Clément Christophe, Marco AF Pimentel, Ronnie Rajan, Praveen K Kanithi•Jan 16, 2025•142

文本生成：從文字描述中產生生動的2D卡通角色
Textoon: Generating Vivid 2D Cartoon Characters from Text Descriptions

Chao He, Jianqiang Ren, Liefeng Bo•Jan 17, 2025•236

多項選擇題：推理使大型語言模型（LLMs）即使錯誤也更加自信
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong

Tairan Fu, Javier Conde, Gonzalo Martínez, María Grandury, Pedro Reviriego•Jan 16, 2025•342

X-Dyna：具表現力的動態人像動畫
X-Dyna: Expressive Dynamic Human Image Animation

Di Chang, Hongyi Xu, You Xie, Yipeng Gao, Zhengfei Kuang, Shengqu Cai, Chenxu Zhang, Guoxian Song, Chao Wang, Yichun Shi, Zeyuan Chen, Shijie Zhou, Linjie Luo, Gordon Wetzstein, Mohammad Soleymani•Jan 17, 2025•142

PaSa：一個用於全面學術論文檢索的LLM代理程序
PaSa: An LLM Agent for Comprehensive Academic Paper Search

Yichen He, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, Weinan E•Jan 17, 2025•4910

HiFi-SR：一個統一的生成式Transformer-卷積對抗網絡，用於高保真語音超分辨率。
HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution

Shengkui Zhao, Kun Zhou, Zexu Pan, Yukun Ma, Chong Zhang, Bin Ma•Jan 17, 2025•93