SOURCE-LINKED INTELLIGENCE

LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video Understanding

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Long-video MLLMs must model temporal change before a limited visual-token budget removes most frame evidence. We introduce LongVU-TTT, which inserts a convolutional Test-Time Training (TTT) resampler with causal fast-weight updates between the vision encoder and the LLM. Its grouped 2D fast weights adapt to each video and contextualize frame features before compression, while a hybrid uniform-and-change-aware selector retains explicit visual evidence for downstream reasoning. Under controlled conditions, TTT-Conv improves over TTT-MLP by up to +2.12 and bidirectional Mamba2 by up to +3.04 on M

Read original source ↗ Open in workspace

recordType

paper

region

Global