WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing Paper • 2603.11593 • Published Mar 12 • 25
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published Dec 30, 2025 • 111
UME-R1 Collection UME-R1 is a framework designed to endow multimodal embedding models with the flexibility to switch between discriminative and generative embeddings • 5 items • Updated Mar 23 • 9
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code Paper • 2508.18106 • Published Aug 25, 2025 • 350
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning Paper • 2503.04812 • Published Mar 4, 2025 • 17
LLaVE Collection LLaVE is a series of large language and vision embedding models trained on a variety of multimodal embedding datasets • 4 items • Updated Mar 10, 2025 • 8
