ChopGrad truncates backpropagation to local frame windows in video diffusion models, reducing memory from linear in frame count to constant while enabling pixel-wise loss fine-tuning.
arXiv preprint arXiv:2511.01419 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TurboTalk uses progressive distillation from 4 steps to 1 step with distribution matching and adversarial training to achieve 120x faster single-step audio-driven talking avatar video generation.
citing papers explorer
-
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
ChopGrad truncates backpropagation to local frame windows in video diffusion models, reducing memory from linear in frame count to constant while enabling pixel-wise loss fine-tuning.
-
TurboTalk: Progressive Distillation for One-Step Audio-Driven Talking Avatar Generation
TurboTalk uses progressive distillation from 4 steps to 1 step with distribution matching and adversarial training to achieve 120x faster single-step audio-driven talking avatar video generation.