AI研究论文每日精选

每日精选AI研究论文及翻译

DSBench：数据科学代理人离成为数据科学专家还有多远？
DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?

Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, Dong Yu•Sep 12, 2024•695

Windows Agent Arena: 在规模上评估多模态操作系统代理
Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Jang, Zack Hui•Sep 12, 2024•482

LLM能够生成新颖的研究思路吗？一项涵盖100多名自然语言处理研究人员的大规模人类研究
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Chenglei Si, Diyi Yang, Tatsunori Hashimoto•Sep 6, 2024•483

IFAdapter：基于实例特征控制的文本到图像生成
IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation

Yinwei Wu, Xianpan Zhou, Bing Ma, Xuefeng Su, Kai Ma, Xinchao Wang•Sep 12, 2024•232

Source2Synth：基于真实数据源的合成数据生成与整理
Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources

Alisia Lupidi, Carlos Gemmell, Nicola Cancedda, Jane Dwivedi-Yu, Jason Weston, Jakob Foerster, Roberta Raileanu, Maria Lomeli•Sep 12, 2024•212

TextBoost：通过微调文本编码器实现文本到图像模型的一次性个性化
TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder

NaHyeon Park, Kunhee Kim, Hyunjung Shim•Sep 12, 2024•164

DreamHOI：基于主体驱动的扩散先验生成3D人体物体交互
DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors

Thomas Hanwen Zhu, Ruining Li, Tomas Jakab•Sep 12, 2024•153

PiTe：用于大型视频-语言模型的像素-时间对齐
PiTe: Pixel-Temporal Alignment for Large Video-Language Model

Yang Liu, Pengxiang Ding, Siteng Huang, Min Zhang, Han Zhao, Donglin Wang•Sep 11, 2024•142

FlashSplat：二维到三维的高斯点云分割的最优解
FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

Qiuhong Shen, Xingyi Yang, Xinchao Wang•Sep 12, 2024•122

基于基础模型，离群目标检测器能学习吗？
Can OOD Object Detectors Learn from Foundation Models?

Jiahui Liu, Xin Wen, Shizhen Zhao, Yingxian Chen, Xiaojuan Qi•Sep 8, 2024•92