arXiv AI

MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation

MemInStream is a new benchmark designed to evaluate memory capabilities in streaming video understanding. It introduces an evidence‑controlled validation protocol that links each question to temporally localized evidence intervals, ensuring that models must rely on historical memory rather than recent observations or linguistic priors. The benchmark covers four key categories—Episodic Retrieval, State Tracking & Updating, Multi‑Evidence Integration, and Contextual Memory—across diverse video scenarios to systematically assess memory performance.

arXiv AI
Sep 30

Watch-Think-Interact: Bootstrapping Long-Horizon Multi-Turn Streaming Video Reasoning with Reinforcement Learning

The paper introduces Watch-Think-Interact (WTI), a closed-loop framework for multi-question streaming video reasoning that maintains compact natural-language memory entries linked to video time ranges. WTI decides whether to answer, continue watching, or recall relevant past intervals for each question, avoiding replay of the full history. The authors build a large dataset, WTI-82K, and a training method, Stream-GDPO, achieving state‑of‑the‑art performance on StreamingBench and OVO-Bench.

By Ziheng Huang, Yicheng Bao, Xueheng Li, Zhenkun Gao, Bangwei Liu, Kunquan Li, Yuxiang Shen, Bangyan Li, Xuejiao Wang, Changbo Wang, Gaoqi He
arXiv AI
Jun 17

LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams

arXiv:2606. 17798v1 Announce Type: cross Abstract: Despite the remarkable progress of Video Large Language Models (Video-LLMs), current online architectures still struggle to simultaneously process continuous video streams, decide autonomously when to respond, and preserve long-horizon contextual memory.

By Zhenyu Yang, Kairui Zhang, Bing Wang, Shengsheng Qian, Changsheng Xu
arXiv Computer Vision
Sep 4

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

The paper introduces LatentStream, a progressive latent working memory framework for streaming video understanding that replaces the traditional store‑and‑retrieve paradigm with a retrieve‑and‑internalize approach. It organizes visual history into short, mid, and long‑term levels using Jenks‑guided adaptive consolidation, then expands memory receptive fields to iteratively retrieve and internalize evidence into a compact latent memory. A confidence‑guided optimization further refines this memory, leading to state‑of‑the‑art performance on online and offline video benchmarks.

By Hongyu Qu, Guangming Yao, Ling Xing, Xiaobin Hu, Rongxing Ding, Guibin Zhang, Fan Zhang, Yi Yuan, Xiangbo Shu, Shuicheng Yan
arXiv Computer Vision
Nov 2

TwinPast: Benchmarking Historical Evidence Use in Streaming Video Understanding with Evidence Contrastive Video Pairs

TwinPast is a new benchmark that tests whether streaming video models use historical evidence by presenting pairs of videos that differ only in critical past events while keeping recent context, questions, and options the same. The study evaluates 34 model configurations on 350 human‑reviewed pairs across five historical tasks, finding that most models rely on recent frames or the question alone, with only a few showing improved performance when historical inputs are provided. Even the best streaming system scores only 49.14% PairAcc, far below general‑purpose models, and case studies reveal that models often select states from the wrong time or contradict the recorded event order.

By Haotian Yang, Yong Chen, Cheng Peng, Haobo Wang, Zhongle Xie, Xuanru Li, Gang Chen
Hugging Face Trending Papers
Sep 3

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

The paper introduces LatentStream, a progressive latent working memory framework for streaming video understanding. It replaces the traditional store‑and‑retrieve approach with a retrieve‑and‑internalize strategy, organizing visual history into short, mid, and long‑term levels and progressively expanding memory receptive fields to internalize evidence into a compact latent memory. The method also employs confidence‑guided optimization to refine memory tokens, achieving state‑of‑the‑art results on online and offline video benchmarks.

arXiv Computer Vision
Oct 2

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

OneStreamer is a streaming video model that jointly learns to record evidence and respond to tasks through a shared proactive generation process. Its Proactive Hierarchical Caption Memory creates time‑grounded local‑detail captions and event summaries, while Proactive State Transition Learning reduces waiting states by supervising all output anchors. The authors also built a large OneStreamer‑1M dataset and show that a 4B model outperforms baselines on eight streaming video benchmarks, with ablations confirming the benefits of generated captions and PSTL.

By Xiangyu Zeng, Yuandong Yang, Zhiqiu Zhang, Yuhan Zhu, Xinhao Li, Qingyi Si, Dingyu Yao, Changlian Ma, Haoran Chen, Xinyu Chen, Yansong Shi, Junhao Zhou, Yifei Li, Jun Zhang, Chuanyu Qin, Chenxu Yang, Xinlei Yu, Kun Ouyang, Yuchen Shao, Qianshan Wei, Changhai Zhou, Jun Gao, Jiaqi Wang, Limin Wang
arXiv AI
Aug 20

EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding

EgoMemReason is a new benchmark for week‑long egocentric video understanding that focuses on memory‑driven reasoning rather than simple perception tasks. It tests three memory types—entity, event, and behavior—across 500 questions, each requiring evidence from an average of 5.1 video segments and 25.9 hours of backtracking. Evaluation of 17 models shows that even the best achieves only 39.6% accuracy, highlighting the difficulty of long‑horizon memory in multimodal systems.

By Ziyang Wang, Yue Zhang, Shoubin Yu, Ce Zhang, Zengqi Zhao, Jaehong Yoon, Hyunji Lee, Gedas Bertasius, Mohit Bansal
arXiv Computer Vision
Sep 30

APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants

arXiv:2609.37559v1 Announce Type: new Abstract: To serve as real-world personal assistants, streaming video models need persistent memory that retains past experiences for later use. Yet existing str...

By Jianguo Huang, Jinming Liu, Qiyao Wang, Liang Xu, Jianhang Li, Zhimian Wen, Mingda Li, Shule Lu, Zhicheng Wang, Yuhan Guo, Xin Jin, Wenjun Zeng
arXiv AI
Sep 30

MemEvo: Automatic Discovery of Streaming Video Memory Mechanisms

MemEvo presents an automated approach to discover memory mechanisms for streaming video understanding. It frames memory design as a search over executable programs expressed in a lightweight domain-specific language, and uses a pretrained large language model to generate and refine candidate memory programs. The framework evaluates each candidate deterministically while keeping the underlying vision-language model frozen, ultimately producing a training-free, bounded-memory mechanism that shows strong performance on StreamingBench and OVO-Bench.

By Guohong Liu, Jialei Ye, Shanhui Zhao, Yunxin Liu, Yuanchun Li