blimp
PulseAugur coverage of blimp — every cluster mentioning blimp across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New research disentangles tokenization algorithms for language models
Researchers have introduced two new tokenization algorithms, BottomUpLL and TopDownComp, to disentangle the effects of optimization objectives and search procedures in language model tokenizers. By creating a 2x2 design…
-
Looped GPT-BERT model trades parameters for computation in language modeling
Researchers have developed a novel language model called Looped GPT-BERT, which achieves comparable performance to existing models on linguistic and downstream tasks while using fewer parameters. This is accomplished by…
-
New benchmark FreqBLiMP tests LLM robustness to rare words
Researchers have developed FreqBLiMP, a new benchmark designed to evaluate the robustness of large language models (LLMs) by controlling for lexical frequency. This extension of the BLiMP benchmark specifically addresse…
-
Transformer models use 'off-axis' computation for concepts, study finds
A new research paper explores the internal workings of Transformer models, revealing that their intermediate states are not random noise but rather a functional component for computing concepts. The study found that a 1…
-
Christopher Nolan's 'The Odyssey' pushes IMAX 70mm boundaries with limited screenings
Christopher Nolan's latest film, 'The Odyssey,' has been released, with a significant portion shot using IMAX film cameras to fill rare 1.43:1 aspect ratio screens. This technical feat was made possible by quieter IMAX …
-
Transformers struggle with "impossible" languages due to generation failures
A new research paper investigates why transformer language models, like GPT-2, struggle with "impossible" languages that humans can acquire. The study found that while these models show some sensitivity to grammaticalit…