{"work":{"id":"9687bd6c-c4f6-4f49-ba59-ca7e825f0710","openalex_id":null,"doi":null,"arxiv_id":"2510.16888","raw_key":null,"title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback","authors":null,"authors_text":"Zongjian Li, Zheyuan Liu, Qihui Zhang, Bin Lin, Feize Wu, Shenghai Yuan","year":2025,"venue":"cs.CV","abstract":"Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their ability to explore and generalize beyond training distributions. To this end, we introduce Edit-R1, a novel post-training framework for instruction-based image editing based on policy optimization. Specifically, we utilize Diffusion Negative-aware Finetuning (DiffusionNFT), a likelihood-free policy optimization method consistent with the flow matching forward process, thereby enabling the use of higher-order samplers and more efficient training. Another key challenge here is the absence of a universal reward model, resulting from the diverse nature of editing instructions and tasks. To bridge this gap, we employ a Multimodal Large Language Model (MLLM) as a unified, training-free reward model, leveraging its output logits to provide fine-grained feedback. Furthermore, we carefully design a low-variance group filtering mechanism to reduce MLLM scoring noise and stabilize optimization. \\texttt{UniWorld-V2}, trained with this framework, achieves \\textbf{state-of-the-art} results on the ImgEdit and GEdit-Bench benchmarks, scoring 4.49 and 7.83, respectively. Crucially, our framework is model-agnostic, delivering substantial performance gains when applied to diverse base models like Qwen-Image-Edit and FLUX-Kontext, demonstrating its wide applicability. Code and models are publicly available to support further research.","external_url":"https://arxiv.org/abs/2510.16888","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T05:40:24.188202+00:00","pith_arxiv_id":"2510.16888","created_at":"2026-05-09T06:55:44.020663+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback","render_title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback"},"hub":{"state":{"work_id":"9687bd6c-c4f6-4f49-ba59-ca7e825f0710","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":21,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-03-10T12:47:53+00:00","last_pith_cited_at":"2026-05-20T18:12:29+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":"2026-06-12T04:19:09.850361+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":6},{"context_role":"baseline","n":5},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"baseline","n":5},{"context_polarity":"background","n":4},{"context_polarity":"unclear","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}