Sparse Autoencoders Find Highly Interpretable Features in Language Models
Paper
• 2309.08600 • Published
• 15
Autoencoder
-
-
In-context Autoencoder for Context Compression in a Large Language Model
Paper • 2307.06945 • Published • 29 -
Self-slimmed Vision Transformer
Paper • 2111.12624 • Published • 1 -
MEMORY-VQ: Compression for Tractable Internet-Scale Memory
Paper • 2308.14903 • Published • 1 -
Adapting Language Models to Compress Contexts
Paper • 2305.14788 • Published • 1 -
Contrastive Audio-Visual Masked Autoencoder
Paper • 2210.07839 • Published • 1 -
Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders
Paper • 2012.00560 • Published • 1 -
Split, Encode and Aggregate for Long Code Search
Paper • 2208.11271 • Published • 1 -
Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach
Paper • 2310.12004 • Published • 2 -
Concept-free Causal Disentanglement with Variational Graph Auto-Encoder
Paper • 2311.10638 • Published • 2 -
Latent Space Factorisation and Manipulation via Matrix Subspace Projection
Paper • 1907.12385 • Published • 1 -
Byte-Level Recursive Convolutional Auto-Encoder for Text
Paper • 1802.01817 • Published