#acceleration2 articles

2 articles

AIBullisharXiv – CS AI · 6h ago1

🧠

Stateful Token Reduction for Long-Video Hybrid VLMs

Researchers developed a new token reduction method for hybrid vision-language models that process long videos, achieving 3.8-4.2x speedup while retaining only 25% of visual tokens. The approach uses progressive reduction and unified scoring for both attention and Mamba blocks, maintaining near-baseline accuracy on long-context video benchmarks.

$NEAR

AIBullisharXiv – CS AI · 6h ago2

🧠

FastBUS: A Fast Bayesian Framework for Unified Weakly-Supervised Learning

Researchers propose FastBUS, a new Bayesian framework for weakly-supervised machine learning that addresses computational inefficiencies in existing methods. The framework uses probabilistic transitions and belief propagation to achieve state-of-the-art results while delivering up to hundreds of times faster processing speeds than current general methods.