paper-with-me

홈 › Papers

StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs

2026-08-13 · Joya Chen, Zeyun Zhong, Mike Zheng Shou arxiv

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, StreamTTT-4B outperforms SimpleStream-4B by 1.4 points in real-time perception and 3.7 points in backward tracing. It also remains competitive with the larger SimpleStream-8B on the Real-Time Visual Understanding (RTVU) subset of StreamingBench. Our code will be released.

📄 PDF Abstract BibTeX arXiv:2608.13416

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks

2025-08-02 · Zihan Zheng, Tianle Cui, Taoran Wang, Fengtao Wang 외 arxiv

Despite significant advances in LLM-driven GUI agents, the field remains constrained by the challenge of reconciling high-fidelity realism with verifiable evaluation accuracy. To address this, we introduce NaturalGAIA, a…

FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer

2023-10-20 · Xinyu Zhang, Li Wang, Zhiqiang Jiang, Kun Dai 외

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods onl…

Homography EstimationPose EstimationVisual Localization

Model selection in reconciling hierarchical time series

2020-10-21 · Mahdi Abolghasemi, Rob J Hyndman, Evangelos Spiliotis, Christoph Bergmeir

Model selection has been proven an effective strategy for improving accuracy in time series forecasting applications. However, when dealing with hierarchical time series, apart from selecting the most appropriate forecas…

modelModel SelectionTime SeriesTime Series Analysis+1

MTA: Multimodal Task Alignment for BEV Perception and Captioning

2024-11-16 · Yunsheng Ma, Burhaneddin Yaman, Xin Ye, Feng Tao 외

Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surro…

Autonomous Driving

Reconciling Multiple Genes Trees via Segmental Duplications and Losses

2018-06-11

Reconciling gene trees with a species tree is a fundamental problem to understand the evolution of gene families. Many existing approaches reconcile each gene tree independently. However, it is well-known that the evolut…