In recent years, multimodal large models have made significant progress in video understanding and reasoning. However, most of them rely on an offline setting, which assumes that both videos and questions can be fully accessed in advance. In contrast, streaming video question answering scenarios require capturing depen...
Shi-Han Wang, Zhen-Yu Yang, Li-Long Liu et al.· Proceedings of the 34th ACM...· 0 citations
Detailed image captioning is usually framed as an amount problem: a model should mention more visual facts while avoiding hallucination. However, autoregressive VLMs generate captions as ordered sequences, and later generations may be produced under weaker or noisier visual grounding. We therefore argue that long-form...
Yuan-Ze Hu, Zhi-Chao Yang, Jun-Wei Jing et al.· 0 citations
Looped Transformers increase effective depth by re-executing shared layers, but three limitations hinder their adoption: memory grows with the loop count, compute can only be adjusted in whole-block steps, and the loop count is hard to change after training. We propose LooM (Loop-invariant Memory), which addresses each...
Le-Le Yang, Mu-Xi Diao, Zhong-Hao Yan et al.· 0 citations
Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a rule-consistent game or narration synchronized to on-screen events. A different route is emerging: multimodal agents that write code to render every frame and synthesize every sound. We introduce VibeVide...
Mu-Xi Diao, Wen-Bin Xu, Le-Le Yang et al.· 1 citation
Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-quality data can substantially improve model reasoning and downstream task performance. However, the upper bound of user simulation is still constrain...
Jiawei Chen, Ruo-Xi Xu, Boxi Cao et al.· 0 citations
OmniBehavior is introduced, the first predictive user simulation benchmark constructed entirely from real-world data, integrating long-horizon, cross-scenario, and heterogeneous behavioral patterns into a unified framework.
Jiawei Chen, Ruo-Xi Xu, Boxi Cao et al.· arXiv.org· 12 citations· ⚡1
Long video understanding relies on video memory to overcome the context limits of multimodal large language models. Existing methods follow a build-then-reasoning pipeline: memory is built offline for the entire video, then reasoned over as a static source. In practice a long video is shared by several questions, and t...
Wei Chen, Xuan-Yu Zheng, Yan-Cheng Long et al.· arXiv.org· 0 citations
The Global State Model (GSM), a causal encoder--decoder architecture that concentrates the selection and aggregation of long-range information in the encoding stage, is introduced, offering a shared-state architecture for efficient language modeling.
Yun Zheng, Bin Wen, Xiao-Jie Wang et al.· arXiv.org· 0 citations
Concentrate and Concentrate (CaC) is a coarse-to-fine anomaly reward model based on Vision-Language Models that first conducts a global temporal scan to anchor anomalous time windows, then performs fine-grained spatial grounding within the localized interval, and finally derives robust judgments via structured spatiote...
Jiyuan Wang, Huan Ouyang, Jiu-Zhou Lin et al.· arXiv.org· 5 citations
These findings establish articulated rationales as a useful complement to behavioral and content signals, and demonstrate a practical role for MLLMs in scaling sparse human explanations into preference information that improves industrial recommendation.
Hao-Ke Xiao, Yue-Yang Liu, Yu-Hui Zhang et al.· 0 citations
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While Thinking-with-Videos enables active temporal perception and Deep Research supports multi-step information seeking, the two capabilities are...
Wenqi Liu, Shi-Jie Ma, Yun-Xiao Wang et al.· 2 citations
Analysis shows that Lngram v2 substantially reduces both total and activated memory parameters while maintaining or improving language modeling performance, and shows that its discrete IDs preserve substantial semantic structure of continuous hidden states, enabling semantic recovery from IDs alone and stable ID--seman...
Yun Zheng, Bin Wen, Xiao-Jie Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.