Tariq Berrada Ifriqi — accepted AI-conference papers

2026

Flowception: Temporally Expansive Flow Matching for Video Generation

Tariq Berrada Ifriqi, John Nguyen, Karteek Alahari, Jakob Verbeek, Ricky T. Q. Chen

CVPR 2026

We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as

Cited by 0 Source ↗code ↗Scholar ↗

2024

Unlocking Pre-trained Image Backbones for Semantic Image Synthesis

Tariq Berrada Ifriqi, Jakob Verbeek, Camille Couprie, Karteek Alahari

CVPR 2024poster

Semantic image synthesis i.e. generating images from user-provided semantic label maps is an important conditional image generation task as it allows to control both the content as well as the spatial layout of generated images. Although diffusion models have pushed the state of the art in generativ…

Cited by 11 Source ↗PDF ↗Scholar ↗