This paper proposes LeWAM, which conditions action generation on JEPA embeddings and models environment evolution by predicting future embeddings in the same space, without relying on a video diffusion backbone, and introduces Demonstration-Guided DPO (DemoDPO), an offline preference refinement stage that derives prefe...
Large-scale vision-language pretrained models like CLIP, paired with parameter-efficient fine-tuning techniques, have emerged as promising solutions for image-to-video transfer in video action recognition. However, existing methods often prioritize strong supervised performance at the expense of transferability and gen...
Meng-Meng Wang, Ze-Yi Huang, Bo-Yuan Jiang et al.· IEEE Transactions on Pattern...· 0 citations
This work presents VideoXAgent, a purely online video-agent harness for long video understanding that starts from the given video file and user query, plans and decomposes the task, invokes specialized expert tools on demand, and aggregates multimodal evidence to produce a final answer while resolving conflicts among o...
Sen Yang, Bo-Qiang Duan, Jing Yang et al.· 2 citations
Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. For example, OpenAI Prism is a free workspace for scientific writing and collaboration. One important feature in Prism is turning scientific diagrams directly into LaTeX TikZ code. In this paper, we build...
Wei-Hao Bo, Shan Zhang, Yanpeng Sun et al.· 1 citation· ⚡1
From-Draft-to-Draft-Free (D2DF), a framework that distills the ability of transforming coarse drafts into refined videos into a one-step video generation model, achieves state-of-the-art performance on multiple metrics, surpassing traditional and multi-step generative methods in both quality and efficiency.
Zi-Zhao Chen, Ping Wei, Guang Dai et al.· arXiv.org· 2 citations
GroundShot is presented, a training-free, model-agnostic agentic framework for entity-grounded multi-shot generation that improves multi-shot consistency over existing methods while requiring no additional training or model modification.
Yixuan Lai, Tianjia Shao, Kun Zhou et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.