{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O34J6CFGYXNZHHNKOAD5W4U6NZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7d2c677493ab0184cb42329307fe60bbebf9cc47e601a1cf50093a22ccc4b9ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:54:04Z","title_canon_sha256":"b45d12a063e95d76b2e8515b865350138747ce6686db225735476271ebeca189"},"schema_version":"1.0","source":{"id":"2506.07986","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07986","created_at":"2026-07-05T11:41:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07986v3","created_at":"2026-07-05T11:41:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07986","created_at":"2026-07-05T11:41:42Z"},{"alias_kind":"pith_short_12","alias_value":"O34J6CFGYXNZ","created_at":"2026-07-05T11:41:42Z"},{"alias_kind":"pith_short_16","alias_value":"O34J6CFGYXNZHHNK","created_at":"2026-07-05T11:41:42Z"},{"alias_kind":"pith_short_8","alias_value":"O34J6CFG","created_at":"2026-07-05T11:41:42Z"}],"graph_snapshots":[{"event_id":"sha256:f32fe0e56597f24ba77796b0ca379d074dc877076d9f4b3929d6c568e88dbbcf","target":"graph","created_at":"2026-07-05T11:41:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation. However, even state-of-the-art MM-DiT models like FLUX struggle with achieving precise alignment between text prompts and generated content. We identify two key issues in the attention mechanism of MM-DiT, namely 1) the suppression of cross-modal attention due to token imbalance between visual and textual modalities and 2) the lack of timestep-aware attention weighting, which hinder the alignment. To address these issues, we propose \\textbf{Temperature-Adjusted Cross-modal Attention ","authors_text":"Chenyang Si, Kwan-Yee K. Wong, Tianlin Pan, Wangmeng Zuo, Zhaoxi Chen, Zhengyao Lv, Ziwei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:54:04Z","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07986","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e65fcb9fa92c7779bb4e1745d7f78157bc6b6cbfb1761ae8f9669d69c5fd8877","target":"record","created_at":"2026-07-05T11:41:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7d2c677493ab0184cb42329307fe60bbebf9cc47e601a1cf50093a22ccc4b9ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:54:04Z","title_canon_sha256":"b45d12a063e95d76b2e8515b865350138747ce6686db225735476271ebeca189"},"schema_version":"1.0","source":{"id":"2506.07986","kind":"arxiv","version":3}},"canonical_sha256":"76f89f08a6c5db939daa7007db729e6e4042e2cff25b0087c79128a693c768e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76f89f08a6c5db939daa7007db729e6e4042e2cff25b0087c79128a693c768e4","first_computed_at":"2026-07-05T11:41:42.893666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:42.893666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KQagm1YWbMQ4oCIx7zpOuM5VxQDdELWoELXaPGGRxj87qm3iy+m7ginPgegXZZlQd/8XzA+f816jhsCYrXBdDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:42.894242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07986","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e65fcb9fa92c7779bb4e1745d7f78157bc6b6cbfb1761ae8f9669d69c5fd8877","sha256:f32fe0e56597f24ba77796b0ca379d074dc877076d9f4b3929d6c568e88dbbcf"],"state_sha256":"623f9be6c12e22659f58ffb62985aee768c782217293dfcc87f964765ade32c4"}