5 papers
Conditioned Activation Transport for T2I Safety Steering
Maciej ChrabÄ szcz, Aleksander Szymczyk, Jan DubiÅski +3
Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inferenc…
Reducing Estimation Uncertainty Using Normalizing Flows and Stratification
PaweÅ Lorek, RafaÅ Nowak, RafaÅ Topolnicki +3
Estimating the expectation of a real-valued function of a random variable from sample data is a critical aspect of statistical analysis, with far-reaching implications in various a…
ELROND: Exploring and decomposing intrinsic capabilities of diffusion models
PaweÅ SkierÅ, Tomasz TrzciÅski, Kamil Deja
A single text prompt passed to a diffusion model often yields a wide range of visual outputs determined solely by stochastic process, leaving users with no direct control over whic…
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
Kevin Wang, Ishaan Javali, MichaÅ Bortkiewicz +2
Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we…
Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
Wojciech Masarczyk, Mateusz Ostaszewski, Tin Sum Cheng +3
The softmax function is a fundamental building block of deep neural networks, commonly used to define output distributions in classification tasks or attention weights in transform…