✨Block Cascading: Training Free Acceleration of Block-Causal Video Models

📝 Summary:
Block Cascading accelerates block-causal video generation via training-free parallelization. It starts future blocks with partially denoised predecessors, transforming sequential pipelines into parallel cascades for a 2x speedup without quality loss.

🔹 Publication Date: Published on Nov 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.20426
• PDF: https://arxiv.org/pdf/2511.20426
• Project Page: https://hmrishavbandy.github.io/block_cascading_page/
• Github: https://hmrishavbandy.github.io/block_cascading_page/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#VideoGeneration #AIAcceleration #ParallelProcessing #DeepLearning #ComputerVision

✨Efficient Document Parsing via Parallel Token Prediction

📝 Summary:
PTP is a novel method to accelerate document parsing by overcoming slow autoregressive decoding in VLMs. It enables parallel token generation using learnable tokens, significantly boosting speed 1.6x-2.2x while reducing hallucinations and showing strong generalization.

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15206
• PDF: https://arxiv.org/pdf/2603.15206

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#DocumentParsing #VLMs #ParallelProcessing #AIEfficiency #NLP