Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual evidence deserves equal attention, as the importance of visual information depends on the content of each video. Motiva...
Teng-Fei Liu, Yang Shi, Yu-Ran Wang et al.· 0 citations
Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observations and insights on multimodal understanding gained from successive generations of Kling. We argue that generation qual...
Kimi Team, Dong Chen, Jia-Lu Chen et al.· 0 citations
OmniPack is proposed, a training-free framework that coordinates structural compression before the LLM with task-relevant semantic refinement within the LLM, and consistently achieves the best performance-efficiency trade-off across diverse retention ratios, outperforming all existing methods.
Wan-Shun Su, Yang Shi, Fei Liu et al.· 2 citations
Human evaluation confirms that RefCaptioner achieves the best overall performance among the open-source models while remaining competitive on standard video captioning benchmarks, and human evaluation further confirms that its captions are preferred by annotators and enable more source-faithful video reconstruction wit...
Teng-Fei Liu, Yang Shi, Yu-Ran Wang et al.· arXiv.org· 0 citations
Beacon, a novel agentic visual reasoning model trained with supervised fine-tuning and reinforcement learning, is proposed, which achieves the highest average score among the evaluated open-source models and ranks first on 11 benchmarks.
Qi-Xun Wang, Yang Shi, Le-Tian Cheng et al.· arXiv.org· 1 citation
FocusMem is introduced, which separates episodic memory and working memory within a compact latent-memory interface and consistently outperforms a fully matched action-only fixed-memory baseline and prior latent memory adaptations.
Zhuoran Zhang, Bowen Li, Jingcheng Ju 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.