Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfol...
Yu-Bo Zhu, Ya-Wen Shao, Zi-Yun Dai et al.· 0 citations
While Vision-Language Models (VLMs) demonstrate strong capabilities, they continue to suffer from a critical limitation: insufficient fine-grained visual perception, which fundamentally limits their multimodal understanding. We attribute this bottleneck to text-dominant optimization biases during pre-training, which en...
Zhe-Han Kan, Yu-Bo Zhu, Xing-Hua Jiang et al.· 0 citations
Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervision. Existing efforts to introduce visual supervision typically do so during post-training, when visual representations have already been la...
Zhe-Han Kan, Xing-Hua Jiang, Yu-Bo Zhu et al.· 0 citations
VGAU-Diag is introduced, a fine-grained evaluation framework for vision generation-assisted understanding that stratifies samples by difficulty, enables unified evaluation of multiple reasoning paradigms, and uses Oracle-Ass Reference Protocols.
Yu-Bo Zhu, Zhe-Han Kan, Jing-Yi Yang et al.· 1 citation
KFS-RAG is proposed, a defense that mitigates information leakage by reformulating the retrieved context by identifying a small set of influential keywords from the retrieved context via an attention rollout plus a causal perturbation mechanism.
Ziliang Zhang, Yu-Bo Zhu, Wei Tong et al.· 0 citations
PURPOSE is proposed, a strict black-box poisoning attack that reframes the injection as an update that minimizes conflict, rather than as a counter-claim, and identifies non-contradicting injection as a practical mode to enhance poisoning attack.
Zijian Wang, Yubo Zhu, M. Dong 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.
