autoencoders

Tag

Cards List
#autoencoders

Learning the Koopman Operator using Attention Free Transformers

arXiv cs.LG · yesterday Cached

This paper introduces attention-free latent memory and dynamic re-encoding to improve long-horizon predictions in Koopman autoencoders, reducing error accumulation on benchmark dynamical systems.

0 favorites 0 likes
#autoencoders

Effects of sparsity and superposition on loss in simple autoencoders

arXiv cs.LG · 2026-06-18 Cached

This paper provides a mathematical analysis of superposition in neural networks, deriving upper and lower bounds on L2 reconstruction loss for simple autoencoders with power activation functions, corroborating empirical findings by Elhage et al.

0 favorites 0 likes
#autoencoders

Physics-conforming Latent Twins

arXiv cs.LG · 2026-06-16 Cached

Physics-conforming Latent Twins is a framework for learning latent surrogate solution operators that enforce physical principles such as conservation laws and dissipative inequalities by design, using a constraint-transfer approach and structure-preserving latent dynamics.

0 favorites 0 likes
#autoencoders

Rational Sparse Autoencoder

arXiv cs.LG · 2026-06-16 Cached

Introduces Rational Sparse Autoencoder (RSAE), which replaces fixed encoder activations with trainable rational functions, improving reconstruction and sparsity trade-offs on residual-stream activations of open-weight language models across multiple baseline families.

0 favorites 0 likes
#autoencoders

@yifeiwang77: Thanks for sharing our work @lateinteraction @sum! The idea is extremely simple: - multi-vector retrieval is so costly …

X AI KOLs Timeline · 2026-05-30 Cached

The author shares their work on reducing the cost of multi-vector retrieval by using k-means as top-1 sparse coding. Omar Khattab adds that late-interaction sparse retrieval with neuron-level inverted indexing on unsupervised sparse autoencoders works well.

0 favorites 0 likes
#autoencoders

@_reachsumit: No More K-means:Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval @Veritas2026 et al. replace vector clus…

X AI KOLs Timeline · 2026-05-29 Cached

This paper proposes Single-stage Sparse Retrieval (SSR), which replaces K-means clustering with sparse autoencoders and inverted indexing, achieving 15x faster indexing and halved retrieval latency while improving accuracy on the BEIR benchmark.

0 favorites 0 likes
#autoencoders

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

Hugging Face Daily Papers · 2026-05-08 Cached

This article introduces Prior-Aligned Autoencoders (PAE), a new method for creating diffusion-friendly latent manifolds that achieves state-of-the-art image generation quality while enabling 13x faster training convergence.

0 favorites 0 likes
#autoencoders

Understanding VQ-VAE (DALL-E Explained Pt. 1)

ML at Berkeley · 2021-02-09 Cached

An educational blog post explaining the Vector Quantized Variational Autoencoder (VQ-VAE) architecture, a key component of OpenAI's DALL-E image generation model.

0 favorites 0 likes
← Back to home

Submit Feedback