P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.
Wan: Open and advanced large-scale video generative models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work empirically shows that many RES-JB SAE features predominantly correspond to simple input statistics. We hypothesize this is caused by a large class imbalance in training data combined with a lack of complex error signals. To reduce this behavior, we propose a method that disentangles token reconstruction from feature reconstruction. This improvement is achieved by introducing a per-token bias, which provides an enhanced baseline for interesting reconstruction. As a result, significantly more interesting features and improved reconstruction in sparse regimes are learned.
years
2026 2representative citing papers
citing papers explorer
-
P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.
- x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability