Open Source
Open-source initiatives are democratizing access to and accelerating advancements in various scientific and technological fields by fostering collaboration and reproducibility. Current research focuses on developing open-source tools and datasets across diverse domains, including AI models (like LLMs and specialized models for tasks such as medical diagnosis or autonomous driving), simulation environments for robotics and network analysis, and benchmarks for evaluating model performance. This open approach significantly benefits the scientific community by enabling wider participation, facilitating rigorous validation, and accelerating the translation of research into practical applications across numerous sectors.
Papers
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
Karolis Jucys, George Adamopoulos, Mehrab Hamidi, Stephanie Milani, Mohammad Reza Samsami, Artem Zholus, Sonia Joseph, Blake Richards, Irina Rish, Özgür Şimşek
VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models
Haodong Duan, Junming Yang, Yuxuan Qiao, Xinyu Fang, Lin Chen, Yuan Liu, Amit Agarwal, Zhe Chen, Mo Li, Yubo Ma, Hailong Sun, Xiangyu Zhao, Junbo Cui, Xiaoyi Dong, Yuhang Zang, Pan Zhang, Jiaqi Wang, Dahua Lin, Kai Chen
An open source Multi-Agent Deep Reinforcement Learning Routing Simulator for satellite networks
Federico Lozano-Cuadra, Mathias D. Thorsager, Israel Leyva-Mayorga, Beatriz Soret
ORAN-Bench-13K: An Open Source Benchmark for Assessing LLMs in Open Radio Access Networks
Pranshav Gajjar, Vijay K. Shah
Ten Years of Teaching Empirical Software Engineering in the context of Energy-efficient Software
Ivano Malavolta, Vincenzo Stoico, Patricia Lago