A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Ronan Collobert, Jason Weston, Léon Bottou, et al.
A unified neural network architecture that learns internal representations from unlabelled data achieves state-of-the-art on multiple NLP tasks without task-specific feature engineering.
Yan Hu, Qingyu Chen, Jingcheng Du, et al.
This paper shows that task-specific prompt engineering, incorporating medical knowledge and few-shot examples, significantly improves GPT-3.5 and GPT-4 performance on clinical NER tasks, though still below BioClinicalBERT.
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, et al.
Jina Embeddings v3 is a 570M parameter multilingual embedding model supporting 8192-token contexts, task-specific LoRA adapters, and flexible dimension reduction via Matryoshka learning.
Unknown
A 1.63B parameter language model that uses control codes to explicitly govern style, content, and task-specific behavior during text generation.
Unknown
MtLoRA introduces task-agnostic and task-specific low-rank adaptation modules for efficient multi-task learning in vision.
A. Narayan, Ines Chami, Laurel J. Orr, et al.
Explores whether foundation models can perform data wrangling tasks without task-specific fine-tuning.
Jinghan Cao, Yu Ma, Xinjin Li, et al.
This paper establishes a quantitative foundation showing that small language models can outperform large ones on task-specific efficiency metrics.
Unknown
This paper explores the potential and challenges of using large language models in healthcare, highlighting their ability to respond to free-text queries without task-specific training.