Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual learning in large language models (LLMs) remains vulnerable to catastrophic forgetting. A promising direction is to identify functionally specialized subnetworks within LLMs th...
Shuo-Ran Jiang, Wen-Tao Zhu, Yang Xiang et al.· 0 citations
VideoVista is presented, a versatile multilingual and multidomain video comprehension benchmark, built via scalable, quality-controlled automatic QA generation and manual refinement, and released at https://github.com/HITsz-TMG/VideoVista.
Yunxin Li, Xin-Yu Chen, Zhenran Xu et al.· IEEE Transactions on Pattern...· 0 citations
DualAnchor is proposed, a gloss-free LLM-based SLT training framework that couples two complementary anchors for linguistically fluent and visually faithful generation that achieves strong overall performance on both PHOENIX-2014T and CSL-Daily.
Hongbin Zhang, Jun-Hao Liu, Xue-Feng Bai et al.· arXiv.org· 0 citations
Empirical analyses show that MoSE improves high-, medium-, and low-resource languages simultaneously, with the largest gains on low-resource speech, thereby breaking the curse of multilinguality without compromising high-resource performance.
Yexing Du, Kaiyuan Liu, You-Cheng Pan 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.
