{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/no-other-representation-component-is-needed","title":"No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves","arxiv_id":"2505.02831","date":"2025-05-05","proceeding":null,"authors":["Dengyang Jiang","Mengmeng Wang","Liuzhuozheng Li","Lei Zhang","Haoyu Wang","Wei Wei","Guang Dai","Yanning Zhang","Jingdong Wang"],"abstract":"Recent studies have demonstrated that learning a meaningful internal representation can both accelerate generative training and enhance the generation quality of diffusion transformers. However, existing approaches necessitate to either introduce an external and complex representation training framework or rely on a large-scale, pre-trained representation foundation model to provide representation guidance during the original generative training process. In this study, we posit that the unique discriminative process inherent to diffusion transformers enables them to offer such guidance without requiring external representation components. We therefore propose Self-Representation Alignment (SRA), a simple yet straightforward method that obtains representation guidance through a self-distillation manner. Specifically, SRA aligns the output latent representation of the diffusion transformer in the earlier layer with higher noise to that in the later layer with lower noise to progressively enhance the overall representation learning during only the generative training process. Experimental results indicate that applying SRA to DiTs and SiTs yields consistent performance improvements. Moreover, SRA not only significantly outperforms approaches relying on auxiliary, complex representation training frameworks but also achieves performance comparable to methods that are heavily dependent on powerful external representation priors.","url_abs":"https://arxiv.org/abs/2505.02831v4","url_pdf":"https://arxiv.org/pdf/2505.02831v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"no-other-representation-component-is-needed","repo_url":"https://github.com/vvvvvjdy/sra","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"SiT-XL + SRA","rank_in_archive_order":28,"of":94,"metrics":{"FID":"1.58"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.02831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02831"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vvvvvjdy/sra","reach":null}],"summary":{"ran":2,"ran_draft_wrong":4,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"60a542850beb08a6","entry":"SRALoss","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60a542850beb08a6"}},{"code_sha256_prefix":"5d15aa12e72b1ecf","entry":"Simpleloss","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d15aa12e72b1ecf"}},{"code_sha256_prefix":"86f835082a2f2ee5","entry":"_build_group_ids_from_counts","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86f835082a2f2ee5"}},{"code_sha256_prefix":"3fe10dc914e6000c","entry":"_compute_group_counts","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fe10dc914e6000c"}},{"code_sha256_prefix":"46649503b5c7e270","entry":"_mix_group_scalars","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46649503b5c7e270"}},{"code_sha256_prefix":"a49bb03f59ee436f","entry":"_normalize_mask_ratios","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a49bb03f59ee436f"}},{"code_sha256_prefix":"9b73352352dc3d0e","entry":"mean_flat","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b73352352dc3d0e"}},{"code_sha256_prefix":"39b170fc9ad7e362","entry":"_expand_group_scalars","repo":"vvvvvjdy/sra","repo_kind":"official","path":"SiT-SRA_DTS_AS/loss.py","file_url":"https://github.com/vvvvvjdy/sra/blob/HEAD/SiT-SRA_DTS_AS/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39b170fc9ad7e362"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}