What Should a Streaming Video Model Remember?

arXiv:2606.16353 · cs.CV, cs.AI · Submitted 2026-06-15 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-06-15

Updated: 2026-09-26

Terminology

• Benchmark — 24× in this paper · explained in 2 episodes
• Embeddings — 15× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Calibration — 10× in this paper · explained in 7 episodes
• Grounding — 8× in this paper · explained in 3 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Surprise-driven Adaptive Windowing — 6× in this paper
• Backward Tracing — 4× in this paper
• Instruction Tuning — 4× in this paper · explained in 2 episodes
• Pruning — 4× in this paper · explained in 4 episodes
• Forward Active Responding — 3× in this paper
• Generalization — 3× in this paper · explained in 13 episodes
• Graph Attention Reasoning — 3× in this paper
• Latent Visual Memory — 3× in this paper
• Real-Time Visual Perception — 3× in this paper
• Benchmarking — 2× in this paper · explained in 3 episodes
• KV cache — 2× in this paper · explained in 3 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• ContextNav: Towards Agentic Multimodal In-Context Learning
• VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
• FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
• MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
• Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams
• GUI Agents for Continual Game Generation
• StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
• StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
• From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
• Thinking in Streaming Video
• PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios
• LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
• A Simple Baseline for Streaming Video Understanding
• RIVER: A Real-Time Interaction Benchmark for Video LLMs
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
• Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
• ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models