A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Nicholas Berente, Bin Gu, Jan Recker, et al.
This editorial frames managing AI as decisions about autonomy, learning, and inscrutability at an evolving frontier, and introduces seven exemplar studies.
Curtis G. Northcutt, Lu Jiang, Isaac L. Chuang
Confident learning estimates uncertainty in dataset labels by identifying label errors using a class-conditional noise model, outperforming seven methods on CIFAR and improving model accuracy.
Olatomiwa O. Bifarin
Tree-based SHAP provides deeper interpretability than PLS-DA VIP scores for explaining machine learning models in metabolomics binary classification.
Peng Zhang, Dingfan Zhang, Wuai Zhou, et al.
This review categorizes AI methods for traditional Chinese medicine network pharmacology into network relationship mining, target positioning, and target navigating, and highlights applications in Cold/Hot syndrome research.
Jürgen Rudolph, Samson Tan, Shannon Tan
An early peer-reviewed exploration of ChatGPT's implications for higher education, focusing on assessment, learning, and teaching, with recommendations for stakeholders.
Unknown
Q-dit introduces a post-training quantization method for diffusion transformers that reduces memory and latency while maintaining generation quality.
Unknown
Lazydit introduces a lazy learning approach to accelerate Diffusion Transformers by selectively skipping redundant computations during inference.
Unknown
This paper formalizes when benchmark contamination is statistically detectable, distinguishing clean benchmarks from low-power audits and proposing power-calibrated detection methods.
Chen An, Fei Huang, Jun Zhang, et al.
Proposes a training-free method to extend the context window of large language models beyond their pretraining length without additional training.
Unknown
The paper shows how to induce large language models to behave like world models by teaching them precondition and effect knowledge about actions.
Unknown
This paper proposes mergeable model-side aggregation states to improve long-context language models on non-additive, set-based aggregation tasks.
Unknown
OC-PRM introduces overcredit-contrastive training to reduce false positives in process reward models, improving step-level verification precision for reasoning LLMs.