SteeringDiffusion supplies a bottlenecked, prompt-conditioned activation interface for frozen diffusion models that delivers smooth monotonic content-style control via one runtime scalar and timestep gating.
The linear representation hypothesis and the geometry of large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Context gating in associative memories boosts inter-memory separation and sparsity for exponential retrieval gains, admits a unique fixed point driven by direct bias and feedback, and matches in-context learning dynamics in transformers like Llama-3.
citing papers explorer
-
SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models
SteeringDiffusion supplies a bottlenecked, prompt-conditioned activation interface for frozen diffusion models that delivers smooth monotonic content-style control via one runtime scalar and timestep gating.
-
Context-Gated Associative Retrieval: From Theory to Transformers
Context gating in associative memories boosts inter-memory separation and sparsity for exponential retrieval gains, admits a unique fixed point driven by direct bias and feedback, and matches in-context learning dynamics in transformers like Llama-3.