Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a generator) trained with incompatible objectives and deployed side by side in retrieval-augmented generation and agent systems. Rec...
Yang Liu, Zhi-Qiang Yuan, Shu-Dong Huang et al.· 0 citations
Evidence-Aligned multimodal on-policy self-Distillation (EAD), which retains the crop-conditioned teacher as the target but constructs a separate evidence reference for weighting the corrections, consistently outperforms previous state-of-the-art methods.
Nan-Xing Hu, Qi-Wei Yan, Jin-Chao Zhang et al.· 0 citations
This paper proposes a ``summarize before grounding''framework (named ``SumGround'') for long-video temporal grounding, and introduces query-guided latent summaries, which is represented as KV states of query-guided prompts, to compress redundant visual tokens into compact query-relevant chunk summaries.
Nan-Xing Hu, Xiao-Yue Duan, Qi-Wei Yan 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.