{"work":{"id":"f6b79552-4f2d-4b7a-9874-6ef1938b8a54","openalex_id":null,"doi":null,"arxiv_id":"2601.16208","raw_key":null,"title":"Scaling text-to-image diffusion transformers with representation autoencoders.arXiv preprint arXiv:2601.16208, 2026","authors":null,"authors_text":"Shengbang Tong, Boyang Zheng, Ziteng Wang, Bingda Tang, Nanye Ma, Ellis Brown, Jihan Yang, Rob Fergus, Yann LeCun, and Saining Xie","year":2026,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2601.16208","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T07:51:15.915508+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T23:09:26.710655+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Scaling text-to-image diffusion transformers with representation autoencoders","render_title":"Scaling text-to-image diffusion transformers with representation autoencoders"},"hub":{"state":{"work_id":"f6b79552-4f2d-4b7a-9874-6ef1938b8a54","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2026-03-15T02:22:27+00:00","last_pith_cited_at":"2026-05-21T04:21:43+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":"2026-06-07T00:01:17.843662+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":7},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":7},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}