-
Sparse Autoencoders Find Highly Interpretable Features in Language Models
Paper • 2309.08600 • Published • 12 -
Language Modeling Is Compression
Paper • 2309.10668 • Published • 82 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 22 -
VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
Paper • 2309.15091 • Published • 32
willwang
willyo
·
AI & ML interests
computer vision
Organizations
None yet
Collections
2
collections about language model with less than 2B parameters
models
None public yet
datasets
None public yet