ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and early warning, and wearable assistants. However, processing continuous video streams with multimodal large language models (MLLMs) is computationally expensive. Existing efforts have explored reducing streaming overhead through visual token pruning, token merging, quantization, on-demand frame retrieval, and context offloading. However, most existing methods overlook the dimension of model depth. Repeatedly executing fu
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%shareAI-lab/learn-claude-code →
“Shared author/contributor keys: yue”
- FuzzySimilar title/name (fuzzy) · 59%VectifyAI/PageIndex →
“Fuzzy title match (0.73): “ShallowStream: Index Shallow then Answer Deep for Streaming ” ≈ “VectifyAI/PageIndex””
- FuzzySimilar title/name (fuzzy) · 59%run-llama/llama_index →
“Fuzzy title match (0.73): “ShallowStream: Index Shallow then Answer Deep for Streaming ” ≈ “run-llama/llama_index””
- FuzzySimilar title/name (fuzzy) · 59%Developer-Y/cs-video-courses →
“Fuzzy title match (0.73): “ShallowStream: Index Shallow then Answer Deep for Streaming ” ≈ “Developer-Y/cs-video-courses””
- LinkedLinked via arxiv author · 85%Jitai Hao →
“ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding”
- LinkedLinked via arxiv author · 85%Ke Yang →
“ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding”
- LinkedLinked via arxiv author · 85%Qiang Huang →
“ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding”
- LinkedLinked via arxiv author · 85%Zhengjun Yue →
“ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding”