STORM teaches LVLMs to internalize spatial-temporal reasoning via bounded latent trajectories trained with generated thought videos in two stages, improving accuracy on VideoMME, MVBench and similar benchmarks while lowering inference overhead.
Slowfast-llava-1.5: A family of token-efficient video large language models for long-form video understanding
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5years
2026 5roles
background 1polarities
background 1representative citing papers
LookWhen factorizes video recognition into learning when, where, and what to compute via uniqueness-based token selection and dual-teacher distillation, achieving better accuracy-FLOPs trade-offs than baselines on multiple datasets.
IPIBench evaluates MLLMs on interactive proactive intelligence in streaming videos, identifies unstable triggering and poor coordination, and proposes the training-free IPI-Agent framework to improve performance across settings.
VidPrism introduces a heterogeneous temporal MoE with content-aware multi-rate sampling and bidirectional fusion for image-to-video transfer, claiming SOTA results on video benchmarks.
Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
citing papers explorer
-
LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
LookWhen factorizes video recognition into learning when, where, and what to compute via uniqueness-based token selection and dual-teacher distillation, achieving better accuracy-FLOPs trade-offs than baselines on multiple datasets.