English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In light of the widespread success of generative models, a significant amountof research has gone into speeding up their sampling time. However, generativemodels are often sampled multiple times to obtain a diverse set incurring acost that is orthogonal to sampling time. We tackle the question of how toimprove diversity and sample efficiency by moving beyond the common assumptionof independent samples. We propose particle guidance, an extension ofdiffusion-based generative sampling where a joint-particle time-evolvingpotential enforces diversity. We analyze theoretically the joint distributionthat particle guidance generates, how to learn a potential that achievesoptimal diversity, and the connections with methods in other disciplines.Empirically, we test the framework both in the setting of conditional imagegeneration, where we are able to increase diversity without affecting quality,and molecular conformer generation, where we reduce the state-of-the-art medianerror by 13% on average.

Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models