pith. sign in

In this setup, a powerful large language model performs cross-modal sequence generation, with tokenized data of all modalities

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows

cs.LG · 2025-12-17 · unverdicted · novelty 6.0

FlowBind enables efficient any-to-any multimodal generation via a shared latent space bridged by modality-specific invertible flows, matching prior quality with up to 6x fewer parameters and 10x faster training.

citing papers explorer

Showing 1 of 1 citing paper.

  • FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows cs.LG · 2025-12-17 · unverdicted · none · ref 4

    FlowBind enables efficient any-to-any multimodal generation via a shared latent space bridged by modality-specific invertible flows, matching prior quality with up to 6x fewer parameters and 10x faster training.