{"work":{"id":"a89f31c1-6a3f-451e-9971-692c11219ea3","openalex_id":null,"doi":null,"arxiv_id":"2504.06256","raw_key":null,"title":"Transfer between Modalities with MetaQueries","authors":null,"authors_text":"Xichen Pan, Satya Narayan Shukla, Aashu Singh, Zhuokai Zhao, Shlok Kumar Mishra, Jialiang Wang","year":2025,"venue":"cs.CV","abstract":"Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We introduce MetaQueries, a set of learnable queries that act as an efficient interface between autoregressive multimodal LLMs (MLLMs) and diffusion models. MetaQueries connects the MLLM's latents to the diffusion decoder, enabling knowledge-augmented image generation by leveraging the MLLM's deep understanding and reasoning capabilities. Our method simplifies training, requiring only paired image-caption data and standard diffusion objectives. Notably, this transfer is effective even when the MLLM backbone remains frozen, thereby preserving its state-of-the-art multimodal understanding capabilities while achieving strong generative performance. Additionally, our method is flexible and can be easily instruction-tuned for advanced applications such as image editing and subject-driven generation.","external_url":"https://arxiv.org/abs/2504.06256","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-04T16:39:58.250680+00:00","pith_arxiv_id":"2504.06256","created_at":"2026-05-09T06:05:35.094635+00:00","updated_at":"2026-07-04T16:39:58.250680+00:00","title_quality_ok":true,"display_title":"Transfer between Modalities with MetaQueries","render_title":"Transfer between Modalities with MetaQueries"},"hub":{"state":{"work_id":"a89f31c1-6a3f-451e-9971-692c11219ea3","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":49,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2025-03-10T12:47:53+00:00","last_pith_cited_at":"2026-06-30T08:29:29+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T05:59:32.710747+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":11},{"context_role":"baseline","n":3},{"context_role":"method","n":3},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":9},{"context_polarity":"baseline","n":3},{"context_polarity":"unclear","n":3},{"context_polarity":"use_method","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}