Self-Edit: Fault-Aware Code Editor for Code Generation

Kavli Affiliate: Zhuo Li | First 5 Authors: Kechi Zhang, Zhuo Li, Jia Li, Ge Li, Zhi Jin | Summary: Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human programming, we […]


Continue.. Self-Edit: Fault-Aware Code Editor for Code Generation

ToolCoder: Teach Code Generation Models to use API search tools

Kavli Affiliate: Zhuo Li | First 5 Authors: Kechi Zhang, Huangzhao Zhang, Ge Li, Jia Li, Zhuo Li | Summary: Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs for specific contexts. These […]


Continue.. ToolCoder: Teach Code Generation Models to use API search tools

ToolCoder: Teach Code Generation Models to use API search tools

Kavli Affiliate: Zhuo Li | First 5 Authors: Kechi Zhang, Huangzhao Zhang, Ge Li, Jia Allen Li, Zhuo Li | Summary: Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs for specific contexts. […]


Continue.. ToolCoder: Teach Code Generation Models to use API search tools

ToolCoder: Teach Code Generation Models to use API search tools

Kavli Affiliate: Zhuo Li | First 5 Authors: Kechi Zhang, Huangzhao Zhang, Ge Li, Jia Li, Zhuo Li | Summary: Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs for specific contexts. These […]


Continue.. ToolCoder: Teach Code Generation Models to use API search tools

Correcting for Interference in Experiments: A Case Study at Douyin

Kavli Affiliate: Huawei Zhang | First 5 Authors: Vivek F. Farias, Hao Li, Tianyi Peng, Xinyuyang Ren, Huawei Zhang | Summary: Interference is a ubiquitous problem in experiments conducted on two-sided content marketplaces, such as Douyin (China’s analog of TikTok). In many cases, creators are the natural unit of experimentation, but creators interfere with each […]


Continue.. Correcting for Interference in Experiments: A Case Study at Douyin

Inspiraling streams of enriched gas observed around a massive galaxy 11 billion years ago

Kavli Affiliate: Ran Wang | First 5 Authors: Shiwu Zhang, Zheng Cai, Dandan Xu, Rhythm Shimakawa, Fabrizio Arrigoni Battaia | Summary: Stars form in galaxies, from gas that has been accreted from the intergalactic medium. Simulations have shown that recycling of gas-the reaccretion of gas that was previously ejected from a galaxy-could sustain star formation […]


Continue.. Inspiraling streams of enriched gas observed around a massive galaxy 11 billion years ago

Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models

Kavli Affiliate: Jing Wang | First 5 Authors: Qiufeng Wang, Xu Yang, Shuxia Lin, Jing Wang, Xin Geng | Summary: During the continuous evolution of one organism’s ancestry, its genes accumulate extensive experiences and knowledge, enabling newborn descendants to rapidly adapt to their specific environments. Motivated by this observation, we propose a novel machine learning […]


Continue.. Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models

The Sloan Digital Sky Survey Reverberation Mapping Project: Key Results

Kavli Affiliate: Linhua Jiang | First 5 Authors: Yue Shen, Catherine J. Grier, Keith Horne, Zachary Stone, Jennifer I. Li | Summary: We present the final data from the Sloan Digital Sky Survey Reverberation Mapping (SDSS-RM) project, a precursor to the SDSS-V Black Hole Mapper Reverberation Mapping program. This data set includes 11-year photometric and […]


Continue.. The Sloan Digital Sky Survey Reverberation Mapping Project: Key Results

The Sloan Digital Sky Survey Reverberation Mapping Project: Key Results

Kavli Affiliate: Luis C. Ho | First 5 Authors: Yue Shen, Catherine J. Grier, Keith Horne, Zachary Stone, Jennifer I. Li | Summary: We present the final data from the Sloan Digital Sky Survey Reverberation Mapping (SDSS-RM) project, a precursor to the SDSS-V Black Hole Mapper Reverberation Mapping program. This data set includes 11-year photometric […]


Continue.. The Sloan Digital Sky Survey Reverberation Mapping Project: Key Results

Constrain the Dark Matter Distribution of Ultra-diffuse Galaxies with Globular-Cluster Mass Segregation: A Case Study with NGC5846-UDG1

Jinning Liang, Fangzhou Jiang, Shany Danieli, Andrew Benson, Phil Hopkins | Summary: [[{“value”:”The properties of globular clusters (GCs) contain valuable information of their host galaxies and dark-matter halos. In the remarkable example of ultra-diffuse galaxy, NGC5846-UDG1, the GC population exhibits strong radial mass segregation, indicative of dynamical-friction-driven orbital decay, which opens the possibility of using […]


Continue.. Constrain the Dark Matter Distribution of Ultra-diffuse Galaxies with Globular-Cluster Mass Segregation: A Case Study with NGC5846-UDG1