A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Aidan P. Thompson, Hasan Metin Aktulga, Richard A. Berger, et al.
This paper serves as the definitive reference for LAMMPS, describing its fundamental algorithms, design strategies for flexibility, and recent capabilities enabled by its extensible architecture.
Unknown
LLM-Evolve introduces a multi-round evaluation framework to assess how LLMs' capabilities evolve across repeated benchmark interactions.
Unknown
AGIEval is a human-centric benchmark designed to evaluate foundation models on human-standardized exams and tasks, providing a more realistic assessment of their capabilities.
Unknown
A review of large language models like ChatGPT in medicine, covering their capabilities, applications, and challenges in clinical practice.
Unknown
A survey of large language models covering their development, capabilities, and applications across text generation, query response, and translation.
Nevan Wichers, Aram Ebtekar, Ariana Azarbal, et al.
Inoculation Prompting (IP) prevents learning of undesired behaviors in LLMs by modifying training prompts to explicitly request the undesired behavior, reducing reward hacking and sycophancy without harming desired capabilities.
Tom Everitt, Cristina Garbacea, Alexis Bellot, et al.
This paper introduces a method to evaluate the goal-directedness of LLMs by measuring how effectively they use their capabilities toward given goals, showing it is consistent across tasks and distinct from task performance.
Hideyuki Takagi
A comprehensive survey of interactive evolutionary computation (IEC), covering applications and interface research to reduce human fatigue, based on about 250 papers.
Xiangxin Meng, Zexiong Ma, Pengfei Gao, et al.
This paper systematically analyzes six LLM-based agent systems for automated bug fixing on the SWE-bench Verified benchmark, comparing their overall performance, fault localization accuracy, and bug reproduction capabilities.
Unknown
This paper introduces Agentic Science as a new stage in AI for Science, tracing its evolution and identifying five core capabilities for autonomous scientific discovery.
Unknown
This paper introduces RT-2, a vision-language-action model that transfers web knowledge to robotic control, enabling improved generalization and new capabilities.
Unknown
This paper introduces a Graph RAG approach for automated short answer grading that provides fine-grained, explainable feedback by returning explicitly linked facts, contrasting with coarse Vector-RAG passages.