Mask-based recognition with multimodal large language models (MLLMs) offers a promising route to vocabulary-free segmentation. However, existing methods typically predict each candidate mask independently, limiting shared-context reasoning, while naive joint multi-mask generation suffers from cross-mask interference. W...
Tao Wang, Gui-Ping Cao, Yi-Peng Zhang et al.· Proceedings of the 34th ACM...· 0 citations
Model merging integrates task-specific fine-tuned models into a single multi-task model, but often suffers from parameter interference caused by conflicting task-vector updates. Existing methods typically mitigate conflicts by pruning task vectors based on weight magnitude or random heuristics, treating Transformers as...
Yan Li, Gui-Ping Cao, Meng-Du Xu et al.· 1 citation
OccAnyScene is proposed, a pixel-frustum-centered Gaussian framework built upon a pretrained depth foundation model which employs Pixel-Aligned Frustum Feature Aggregation to construct a camera-aware frustum query for each feature pixel, and Frustum-Parameterized Gaussian Construction to decode each query into multiple...
Junjie Liu, Wan-Shui Gan, Zi-Tong Dai et al.· 0 citations
Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable perturbations in a text-anchored semantic space and integrates Text-Anchored Semantic Factorization (TASF), which encourages the separation of cross-modal semantic factors from modality-specific residuals.
Wenyun Li, Gui-Ping Cao, Xiang-Yuan Lan 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.