pith. sign in

Scaling vision transformers to gigapixel images via hierarchical self-supervised learning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1 cs.LG 1

years

2024 2

roles

background 1

polarities

background 1

representative citing papers

LTX-Video: Realtime Video Latent Diffusion

cs.CV · 2024-12-30 · conditional · novelty 6.0

LTX-Video integrates Video-VAE and transformer for 1:192 latent compression and real-time video diffusion by moving patchifying to the VAE and letting the decoder finish denoising in pixel space.

citing papers explorer

Showing 2 of 2 citing papers.

  • FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision cs.LG · 2024-07-11 · accept · none · ref 11

    FlashAttention-3 achieves 1.5-2x speedup on H100 GPUs for attention, reaching 740 TFLOPs/s (75% utilization) in FP16 and near 1.2 PFLOPs/s in FP8 while cutting numerical error by 2.6x versus baseline FP8 attention.

  • LTX-Video: Realtime Video Latent Diffusion cs.CV · 2024-12-30 · conditional · none · ref 23

    LTX-Video integrates Video-VAE and transformer for 1:192 latent compression and real-time video diffusion by moving patchifying to the VAE and letting the decoder finish denoising in pixel space.