A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This review comprehensively evaluates protein language models and their encoding strategies for protein function prediction, aiming to help researchers understand and apply these models.
Unknown
This paper proposes locality-based encoding and model quantization to improve efficiency of hyper-dimensional computing for machine learning tasks.
Unknown
FastVLM introduces an efficient vision encoding method that reduces computational cost while maintaining high performance in text-rich image understanding tasks.
Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, et al.
A comprehensive survey of deep learning-based image captioning, covering visual encoding, text generation, training strategies, datasets, and evaluation metrics.
Bradley Butcher, Michael O'Keefe, James Titchener
This paper introduces a length-difference positional encoding (LDPE) method to fine-tune LLMs for precise response length control, achieving mean token errors under 3 tokens.
Unknown
LMDX adapts arbitrary LLMs for document information extraction with layout encoding and grounding to prevent hallucinations.
Hangbo Bao, Li Dong, Furu Wei, et al.
UniLMv2 introduces Pseudo-Masked Language Modeling (PMLM) to unify autoencoding and partially autoregressive objectives, improving performance across diverse NLP tasks.
Zhilin Yang, Zihang Dai, Yiming Yang, et al.
XLNet combines autoregressive and autoencoding pretraining via permutation language modeling, outperforming BERT on NLP tasks.
Zihang Dai, Zhilin Yang, Yiming Yang, et al.
TransformerXL extends the Transformer model with segment-level recurrence and relative positional encoding to handle long sequences beyond fixed-length contexts.
Thomas Müller, Alex Evans, Christoph Schied, et al.
A multiresolution hash encoding enables training high-quality neural graphics primitives in seconds and rendering in milliseconds.