Search papers, labs, and topics across Lattice.
People's Public Security University of China
3
0
6
Existing corpus poisoning attacks falter in realistic RAG systems, but the new CRCP framework ensures adversarial effectiveness by aligning chunking and reranking processes.
Ditching modular architectures unlocks surprisingly competitive vision-language performance, proving that end-to-end pixel-to-word models can rival traditional approaches at scale.
By decoupling semantic reasoning from spatial grounding, AnchorSeg achieves unprecedented accuracy in reasoning segmentation tasks.
