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.
arXiv:2604. 25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms.
The paper introduces “P…IBench”, a benchmark for proactive video understanding that tests daily perception, risk prediction, and intervention in real‑life streaming scenarios. It evaluates 12 video‑language models, finding that current systems struggle to make well‑calibrated response decisions. The authors also create new proactive training data and train “P…I-Assistant-4B”, which shows uneven improvements across the benchmark’s capabilities.
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.
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.
arXiv:2610.16927v1 Announce Type: new Abstract: Short-video search requires compact query rewriters that infer personalized intent from brief, ambiguous queries under strict latency constraints. The...
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily...
ProactEgoMem is a benchmark for evaluating proactive memory in streaming egocentric video, focusing on three tasks—Information Capture, State Tracking, and Location Tracking—to reflect real-world environmental needs. It introduces two levels of proactiveness: Notification Level, which requires a single timely alert, and Intervention Level, which demands continuous memory maintenance via an active tool lifecycle. The benchmark includes daily and scientific datasets with corresponding QA sets, and shows that current models struggle to capture memory both timely and accurately.
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...
arXiv:2607. 11523v1 Announce Type: cross Abstract: When should an intelligent assistant speak up without being asked?
The paper introduces MaLoW, a streaming memory framework that internalizes long‑term video history into evolving lightweight parameter updates using a recurrent HyperNetwork and LoRA weights. MaLoW keeps current observations as input while carrying historical context forward without re‑visiting the full video stream. The authors also present MaLoW‑Instruct, a large streaming video dataset, and show that MaLoW outperforms prior memory methods on several benchmarks and improves action success in a vision‑language‑action setting.
Today's multimodal assistants are typically prompted to interpret the visual evidence presented to them. To offload the cognitive burden of remembering across long horizons, wearable assistants should...