Real-time Collaboration, Text Editing, Conflict Resolution, Google Docs
F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model
arxiv.org·11h
Do Multimodal LLMs See Sentiment?
arxiv.org·11h
QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting
arxiv.org·11h
The AI Data Scientist
arxiv.org·11h
Loading...Loading more...