A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Richard C. Mohs, Nigel H. Greig
This paper outlines the drug discovery and development process to help basic scientists frame their research for effective translation to clinical use.
Melvin Johnson, Mike Schuster, Quoc V. Le, et al.
Proposes a single multilingual NMT model using a target-language token for zero-shot translation across multiple language pairs.
Michel Callon, Jean-Pierre Courtial, William A. Turner, et al.
This paper introduces co-word analysis as a method for mapping the dynamics of science and technology through the co-occurrence of keywords in publications.
Rui Zhu, Xi Cheng, Keliang Liu, et al.
SheetCompressor compresses spreadsheets for LLMs via structural anchors, inverse index translation, and data-aware aggregation, enabling Chain of Spreadsheet for QA.
Unknown
DePlot standardizes plot-to-table translation, converting plots into linearized tables for LLM processing.
Unknown
Introduced the Transformer model with multihead attention for language translation, replacing recurrent architectures.
Deepon Halder, Angira Mukherjee
Fine-tunes Gemma3–4B-IT to create a translation model supporting 22 Indian languages.
Unknown
PaLM 2 improves upon PaLM with multilingual training, multiple objectives, and enhanced reasoning, coding, and translation performance.
Unknown
mBART pre-trains a multilingual sequence-to-sequence denoising auto-encoder on large-scale monolingual corpora using the BART objective, significantly improving machine translation.
Unknown
XLM-RoBERTa scales multilingual masked language modeling to 100 languages, achieving strong cross-lingual transfer without translation objectives.
Unknown
Marian is a fast, self-contained C++ neural machine translation framework with dynamic computation graphs and minimal dependencies.
Ashish Vaswani, Noam Shazeer, Niki Parmar, et al.
Introduced the Transformer architecture, replacing recurrence and convolutions with self-attention mechanisms, achieving state-of-the-art results on machine translation and becoming the foundation for all modern large language models.