RestGPT: Connecting Large Language Models with Real-World RESTful APIs

Kavli Affiliate: Ke Wang | First 5 Authors: Yifan Song, Weimin Xiong, Dawei Zhu, Wenhao Wu, Han Qian | Summary: Tool-augmented large language models (LLMs) have achieved remarkable progress in tackling a broad range of tasks. However, existing methods are mainly restricted to specifically designed tools and fail to fulfill complex instructions, having great limitations […]


Continue.. RestGPT: Connecting Large Language Models with Real-World RESTful APIs

An Empirical Study of Bugs in Quantum Machine Learning Frameworks

Kavli Affiliate: Zhuo Li | First 5 Authors: Pengzhan Zhao, Xiongfei Wu, Junjie Luo, Zhuo Li, Jianjun Zhao | Summary: Quantum computing has emerged as a promising domain for the machine learning (ML) area, offering significant computational advantages over classical counterparts. With the growing interest in quantum machine learning (QML), ensuring the correctness and robustness […]


Continue.. An Empirical Study of Bugs in Quantum Machine Learning Frameworks

Galaxy Light profile neural Networks (GaLNets). II. Bulge-Disc decomposition in optical space-based observations

Kavli Affiliate: Hu Zhan | First 5 Authors: Chen Qiu, Nicola R. Napolitano, Rui Li, Yuedong Fang, Crescenzo Tortora | Summary: Bulge-disk (B-D) decomposition is an effective diagnostic to characterize the galaxy morphology and understand its evolution across time. So far, high-quality data have allowed detailed B-D decomposition to redshift below 0.5, with limited excursions […]


Continue.. Galaxy Light profile neural Networks (GaLNets). II. Bulge-Disc decomposition in optical space-based observations

Galaxy Light profile neural Networks (GaLNets). II. Bulge-Disc decomposition in optical space-based observations

Kavli Affiliate: Hu Zhan | First 5 Authors: Chen Qiu, Nicola R. Napolitano, Rui Li, Yuedong Fang, Crescenzo Tortora | Summary: Bulge-disk (B-D) decomposition is an effective diagnostic to characterize the galaxy morphology and understand its evolution across time. So far, high-quality data have allowed detailed B-D decomposition to redshift below 0.5, with limited excursions […]


Continue.. Galaxy Light profile neural Networks (GaLNets). II. Bulge-Disc decomposition in optical space-based observations

Online Multi-Contact Receding Horizon Planning via Value Function Approximation

Kavli Affiliate: Ke Wang | First 5 Authors: Jiayi Wang, Sanghyun Kim, Teguh Santoso Lembono, Wenqian Du, Jaehyun Shim | Summary: Planning multi-contact motions in a receding horizon fashion requires a value function to guide the planning with respect to the future, e.g., building momentum to traverse large obstacles. Traditionally, the value function is approximated […]


Continue.. Online Multi-Contact Receding Horizon Planning via Value Function Approximation

WELL: Applying Bug Detectors to Bug Localization via Weakly Supervised Learning

Kavli Affiliate: Zhuo Li | First 5 Authors: Zhuo Li, Huangzhao Zhang, Zhi Jin, Ge Li, | Summary: Bug localization, which is used to help programmers identify the location of bugs in source code, is an essential task in software development. Researchers have already made efforts to harness the powerful deep learning (DL) techniques to […]


Continue.. WELL: Applying Bug Detectors to Bug Localization via Weakly Supervised Learning

Resolving the Binary Components of the Outbursting Protostar HBC 494 with ALMA

Kavli Affiliate: Gregory J. Herczeg | First 5 Authors: Pedro Henrique Nogueira, Alice Zurlo, Sebastián Pérez, Camilo González-Ruilova, Lucas A. Cieza | Summary: Episodic accretion is a low-mass pre-main sequence phenomenon characterized by sudden outbursts of enhanced accretion. These objects are classified into two: protostars with elevated levels of accretion that lasts for decades or […]


Continue.. Resolving the Binary Components of the Outbursting Protostar HBC 494 with ALMA

Unveiling the small-scale jets in the rapidly growing supermassive black hole IZw1

Kavli Affiliate: Ran Wang | First 5 Authors: Xiaolong Yang, Su Yao, Luigi C. Gallo, Jun Yang, Luis C. Ho | Summary: Accretion of black holes at near-Eddington or super-Eddington rates is the most powerful episode that drives black hole growth, and it may work in several types of objects. However, the physics of accretion […]


Continue.. Unveiling the small-scale jets in the rapidly growing supermassive black hole IZw1