GenRouter: Unified Workflow Routing for Agentic Image Generation Paper • 2608.16721 • Published 5 days ago • 24
Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning Paper • 2606.29812 • Published Jun 29
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation Paper • 2606.29805 • Published Jun 30
Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis? Paper • 2607.17262 • Published Jul 19
AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval Paper • 2608.08732 • Published 13 days ago
mDenseOn & mLateOn Collection A collection of open state-of-the-art single and multi-vector models and datasets for multilingual, long context and code retrieval • 19 items • Updated 16 days ago • 18
Nemotron 3 Embed Collection Open embedding models for enterprise RAG, agentic retrieval, code search, and agent memory. • 3 items • Updated 11 days ago • 37
UEmbed: Unified Sparse and Dense Multimodal Embeddings Paper • 2608.02583 • Published 19 days ago • 50
MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework Paper • 2606.07654 • Published Jun 3