{"work":{"id":"9a5ed1ec-27cf-442b-b350-3016e61aed26","openalex_id":null,"doi":null,"arxiv_id":"2602.04770","raw_key":null,"title":"Generative Modeling via Drifting","authors":null,"authors_text":"Mingyang Deng, He Li, Tianhong Li, Yilun Du, Kaiming He","year":2026,"venue":"cs.LG","abstract":"Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and flow-based models. In this paper, we propose a new paradigm called Drifting Models, which evolve the pushforward distribution during training and naturally admit one-step inference. We introduce a drifting field that governs the sample movement and achieves equilibrium when the distributions match. This leads to a training objective that allows the neural network optimizer to evolve the distribution. In experiments, our one-step generator achieves state-of-the-art results on ImageNet at 256 x 256 resolution, with an FID of 1.54 in latent space and 1.61 in pixel space. We hope that our work opens up new opportunities for high-quality one-step generation.","external_url":"https://arxiv.org/abs/2602.04770","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-14T01:33:35.028633+00:00","pith_arxiv_id":"2602.04770","created_at":"2026-05-10T09:33:41.667871+00:00","updated_at":"2026-05-14T17:03:06.181135+00:00","title_quality_ok":false,"display_title":"Generative Modeling via Drifting","render_title":"Generative Modeling via Drifting"},"hub":{"state":{"work_id":"9a5ed1ec-27cf-442b-b350-3016e61aed26","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":24,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2026-03-30T14:34:32+00:00","last_pith_cited_at":"2026-05-12T14:26:31+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":"2026-05-14T21:56:15.479475+00:00","tier_text":"hub"},"tier":"hub","role_counts":[],"polarity_counts":[],"runs":{},"summary":{},"graph":{},"authors":[]}}