A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Xunyu Zhu, Jian Li, Yong Liu, et al.
This survey reviews model compression techniques for large language models, covering quantization, pruning, and knowledge distillation, along with benchmarking and evaluation metrics.
Zhengxia Zou, Keyan Chen, Zhenwei Shi, et al.
A comprehensive survey tracing 25 years of object detection evolution, from 1990s hand-crafted methods to modern deep learning detectors, covering milestones, datasets, metrics, and architectures.
Juan R. Terven, Diana Margarita Córdova Esparza, Julio-Alejandro Romero-González, et al.
A comprehensive survey of loss functions and metrics in deep learning, offering a unified framework, multi-loss insights, and guidance for modern tasks like RAG.
B.‐C. CHEN, Zhaofeng Zhang, Nicolas Langrené, et al.
This review surveys foundational and advanced prompt engineering techniques for LLMs and VLMs, evaluates them with subjective and objective metrics, and examines prompt engineering's role in AI security.
Parinthapat Pengpun, Simran Khanuja, Graham Neubig
Introduces knowledge-graph structural rarity metrics for multimodal entity linking, a training-free reasoning+retrieval framework, and MERLIN-Rare, improving SOTA by 6.9% overall and up to 23.3% on rare entities.
Micah Hodosh, Peter Young, Julia Hockenmaier
Frames image description as a ranking task, introducing a benchmark of 8,000 images with five captions each and showing that ranking-based evaluation can be automated.
Dairu Liu, Zekun Qi, Jiayu Zeng, et al.
HumanTracker introduces a large-scale, perceptually aligned benchmark and preference-based metric for evaluating humanoid motion tracking, revealing failures that kinematic metrics miss.
Ali Borji, Ming-Ming Cheng, Qibin Hou, et al.
A comprehensive survey of salient object detection covering 228 publications, including roots, core techniques, datasets, evaluation metrics, and future directions.
Yijia Xiao, Wanjia Zhao, Junkai Zhang, et al.
This paper provides the first comprehensive overview of Protein LLMs, covering architectures, training datasets, evaluation metrics, and applications, with a structured taxonomy from over 100 articles.
Unknown
The paper introduces a Common Task Framework (CTF) for scientific machine learning, featuring curated datasets and task-specific metrics to enable critical evaluation of algorithms.
Unknown
This paper presents methods, metrics, and comparisons for uncertainty quantification in scientific machine learning, along with an open-source Python library.
Unknown
This paper argues that AI safety benchmarks may not actually measure safety progress due to the Bitter Lesson and scaling, suggesting safety metrics could be correlated with capabilities.