StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. Prior work shows that shortening the context can sharpen current-scene perception at the expense of long-range recall. To reconcile these abilities, we introduce StreamTTT, which writes long-range history into online-updated fast weights outside the attention context. This leaves a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution. We train StreamTTT jointly on offline long-video QA and a newly constructed real-time QA corpus. On OVO-Bench, under each model's reported input protocol, StreamTTT-4B outp...
| Authors | Joya Chen, Zeyun Zhong, Mike Zheng Shou |
|---|---|
| Primary category | cs.CV |
| Published | 13 August 2026 |
| Last updated at source | 10 September 2026 |
Connected in the knowledge graph
- zeyun-zhong/RealTimeVideo-Instruct-112KDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.