Streaming Video-LMM. Start with Six Development Paths from 2023 to 2026 for a map of query visibility, memory budgets, retrieval, interaction, and streaming evaluation.
Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning.
Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding.
A short index of benchmarks used by recent streaming and long-video VLM papers.
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge.
A pipeline view of recent long streaming video understanding papers.
Streaming Token Compression for Efficient Video Understanding.
Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval.
Query-Agnostic KV Cache Memory for Streaming Video Understanding.
Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs.
Memory-Constrained KV Cache Compression for Streaming Video Understanding.