TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs
cs.CV
Submitted: 2026-10-30
Updated: 2026-11-15
Code: https://github.com/Yh1zzzzzzz/TwinPast_code
Terminology
Sources
- TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
- StreamFlow: Dynamic Memory Flows for Streaming Video Understanding
- AURA: Always-On Understanding and Real-Time Assistance via Video Streams
- video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
- Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
- JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
- OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
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