MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation
cs.CV, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- A Simple Baseline for Streaming Video Understanding
- OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
- S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval
- TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
- EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos
- AURA: Always-On Understanding and Real-Time Assistance via Video Streams
- JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
- APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
- Qwen2.5-VL Technical Report
- Qwen3-VL Technical Report
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs