Large Language Model
Model Collapse Demystified: The Case of Regression Elvis Dohmatob Y unzhen Feng Julia Kempe FAIR, Meta Center for Data Science, New York University
The phenomenon of "model collapse" refers to the situation whereby as a model is trained recursively on data generated from previous generations of itself over time, its performance degrades until the model eventually becomes completely useless, i.e. the model collapses.
Exploring Molecular Pretraining Model at Scale
The Uni-Mol2 with 1.1B parameters also outperforms
529d8b3a23991e83db07f21727256374-Paper-Datasets_and_Benchmarks_Track.pdf
To evaluate MLLMs' A VR abilities systematically, we introduce
SparseLLM: Towards Global Pruning of Pre-trained Language Models
Pruning has emerged as a pivotal compression strategy, introducing sparsity to enhance both memory and computational efficiency.
Learning to Understand: Identifying Interactions via the Mobius Transform
One of the key challenges in machine learning is to find interpretable representations of learned functions.